Repo: ml-agents
Filename: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/projects/ml-agents/ml-agents/mlagents/trainers/tests/test_simple_rl.py
ClassName: none
Testname: test_recurrent_ppo
Params: learning_rate,226,50,ParamType.LR,0.001
max_steps,232,18,ParamType.ITER,5000
Assertion: assert all(reward > success_threshold for reward in processed_rewards)
Original runtime: 127.575
>>Getting original runtime
Optimization Iteration: 1
Running with params: {'learning_rate': 0.001, 'max_steps': 5000}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.001_5000
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 18...
Iter 19...
Iter 20...
Iter 21...
Iter 22...
Iter 23...
Iter 24...
Iter 25...
Iter 26...
Iter 27...
Iter 28...
Iter 29...
Timings: Avg: 123.81733333333335, Max: 127.03, Min: 120.29
Passed tests : 30
Failed tests : 0
Converged: True
Convergence score: 0.0
Evaluating 30 values out of 30
Overall-timings: Avg: 123.81733333333335, Max: 127.03, Min: 120.29
Variance (0.0) too small, using delta distribution
Variance (4.930380657631324e-32) too small, using delta distribution
Probability of fail : 0.0
All-Passed: True
Probabilty of failure: 0.0
Runtime: 123.81733333333335
Score: 123.81733333333335
Best-score: 123.81733333333335
Best-param: {'learning_rate': 0.001, 'max_steps': 5000}
>>Setting original runtime to 123.81733333333335
Optimization Iteration: 1
Running with params: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.08166178827568872_1200
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 18...
Iter 19...
Iter 20...
Iter 21...
Iter 22...
Iter 23...
Iter 24...
Iter 25...
Iter 26...
Iter 27...
Iter 28...
Iter 29...
Timings: Avg: 32.281, Max: 32.65, Min: 31.279999999999998
Passed tests : 30
Failed tests : 0
Converged: True
Convergence score: 0.0
Evaluating 30 values out of 30
Overall-timings: Avg: 32.281, Max: 32.65, Min: 31.279999999999998
Variance (4.930380657631324e-32) too small, using delta distribution
Variance (4.930380657631324e-32) too small, using delta distribution
Probability of fail : 0.0
All-Passed: True
Probabilty of failure: 0.0
Runtime: 32.281
Score: 32.281
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 2
Running with params: {'learning_rate': 0.061449101089881684, 'max_steps': 100}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.061449101089881684
Optimization Iteration: 3
Running with params: {'learning_rate': 0.0031770449284957724, 'max_steps': 3200}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.0031770449284957724
Optimization Iteration: 4
Running with params: {'learning_rate': 5.972133148627777e-05, 'max_steps': 500}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 5.972133148627777e-05
Optimization Iteration: 5
Running with params: {'learning_rate': 0.048411924658091784, 'max_steps': 400}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.048411924658091784
Optimization Iteration: 6
Running with params: {'learning_rate': 0.0201635489469904, 'max_steps': 500}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.0201635489469904
Optimization Iteration: 7
Running with params: {'learning_rate': 3.504315961497637e-05, 'max_steps': 4100}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 3.504315961497637e-05
Optimization Iteration: 8
Running with params: {'learning_rate': 0.05361097633291208, 'max_steps': 1400}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.05361097633291208
Optimization Iteration: 9
Running with params: {'learning_rate': 0.039372428936164425, 'max_steps': 100}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.039372428936164425
Optimization Iteration: 10
Running with params: {'learning_rate': 2.7515064159204703e-05, 'max_steps': 100}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 2.7515064159204703e-05
Optimization Iteration: 11
Running with params: {'learning_rate': 3.859102143097111e-05, 'max_steps': 400}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 3.859102143097111e-05
Optimization Iteration: 12
Running with params: {'learning_rate': 0.018954202682830882, 'max_steps': 500}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.018954202682830882
Optimization Iteration: 13
Running with params: {'learning_rate': 0.004527512571490464, 'max_steps': 100}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.004527512571490464
Optimization Iteration: 14
Running with params: {'learning_rate': 0.0001046736698954455, 'max_steps': 300}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.0001046736698954455
Optimization Iteration: 15
Running with params: {'learning_rate': 0.00011010668272769681, 'max_steps': 1100}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.00011010668272769681
Optimization Iteration: 16
Running with params: {'learning_rate': 0.00018477920819333658, 'max_steps': 500}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.00018477920819333658
Optimization Iteration: 17
Running with params: {'learning_rate': 0.01233125945239002, 'max_steps': 300}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.01233125945239002
Optimization Iteration: 18
Running with params: {'learning_rate': 0.0001727933491586316, 'max_steps': 300}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.0001727933491586316
Optimization Iteration: 19
Running with params: {'learning_rate': 0.27454677523165427, 'max_steps': 300}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.27454677523165427_300
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 18...
Iter 19...
Iter 20...
Iter 21...
Iter 22...
Iter 23...
Iter 24...
Iter 25...
Iter 26...
Iter 27...
Iter 29...
Iter 28...
Timings: Avg: 17.23933333333333, Max: 17.44, Min: 16.9
Passed tests : 0
Failed tests : 30
Half of samples failed, exiting...
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 20
Running with params: {'learning_rate': 0.18860388518468377, 'max_steps': 400}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.18860388518468377_400
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 18...
Iter 19...
Iter 20...
Iter 21...
Iter 22...
Iter 23...
Iter 24...
Iter 25...
Iter 26...
Iter 27...
Iter 28...
Iter 29...
Timings: Avg: 18.442333333333334, Max: 18.6, Min: 18.290000000000003
Passed tests : 0
Failed tests : 30
Half of samples failed, exiting...
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 21
Running with params: {'learning_rate': 0.0005384455668860876, 'max_steps': 2000}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.0005384455668860876
Optimization Iteration: 22
Running with params: {'learning_rate': 0.9299021949154775, 'max_steps': 900}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.9299021949154775_900
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 18...
Iter 19...
Iter 20...
Iter 21...
Iter 22...
Iter 23...
Iter 24...
Iter 25...
Iter 26...
Iter 27...
Iter 28...
Iter 29...
Timings: Avg: 40.653333333333336, Max: 41.48, Min: 39.84
Passed tests : 30
Failed tests : 0
Converged: True
Convergence score: 0.0
Evaluating 30 values out of 30
Overall-timings: Avg: 40.653333333333336, Max: 41.48, Min: 39.84
Variance (0.0) too small, using delta distribution
Variance (0.0) too small, using delta distribution
Probability of fail (non-zero): 1.0
Exceeding max probability of failure: 1.0
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 23
Running with params: {'learning_rate': 0.2346774610310187, 'max_steps': 2100}
Higher iteration... returning...
Optimization Iteration: 24
Running with params: {'learning_rate': 0.0009365904493660737, 'max_steps': 2100}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.0009365904493660737
Optimization Iteration: 25
Running with params: {'learning_rate': 0.9407752704778248, 'max_steps': 900}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.9407752704778248_900
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 18...
Iter 19...
Iter 20...
Iter 21...
Iter 22...
Iter 23...
Iter 24...
Iter 25...
Iter 26...
Iter 27...
Iter 28...
Iter 29...
Timings: Avg: 36.68499999999998, Max: 38.07, Min: 35.279999999999994
Passed tests : 0
Failed tests : 30
Half of samples failed, exiting...
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 26
Running with params: {'learning_rate': 0.2807571751046182, 'max_steps': 5000}
Higher iteration... returning...
Optimization Iteration: 27
Running with params: {'learning_rate': 0.000887716387676938, 'max_steps': 2600}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.000887716387676938
Optimization Iteration: 28
Running with params: {'learning_rate': 0.950059143761717, 'max_steps': 800}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.950059143761717_800
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 18...
Iter 19...
Iter 20...
Iter 21...
Iter 23...
Iter 22...
Iter 24...
Iter 25...
Iter 26...
Iter 27...
Iter 29...
Iter 28...
Timings: Avg: 39.84566666666667, Max: 40.739999999999995, Min: 38.89
Passed tests : 0
Failed tests : 30
Half of samples failed, exiting...
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 29
Running with params: {'learning_rate': 0.13082074098098714, 'max_steps': 4700}
Higher iteration... returning...
Optimization Iteration: 30
Running with params: {'learning_rate': 0.0008897112908306968, 'max_steps': 2900}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.0008897112908306968
Optimization Iteration: 31
Running with params: {'learning_rate': 0.5518265838541493, 'max_steps': 1500}
Higher iteration... returning...
Optimization Iteration: 32
Running with params: {'learning_rate': 0.13493220974770645, 'max_steps': 4100}
Higher iteration... returning...
Optimization Iteration: 33
Running with params: {'learning_rate': 0.0055952355280459425, 'max_steps': 3000}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.0055952355280459425
Optimization Iteration: 34
Running with params: {'learning_rate': 0.42378889426374283, 'max_steps': 1200}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.42378889426374283_1200
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 16...
Iter 15...
Iter 17...
Iter 18...
Iter 19...
Iter 20...
Iter 21...
Iter 22...
Iter 23...
Iter 24...
Iter 25...
Iter 26...
Iter 27...
Iter 28...
Iter 29...
Timings: Avg: 30.537000000000003, Max: 31.130000000000003, Min: 29.75
Passed tests : 0
Failed tests : 30
Half of samples failed, exiting...
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 35
Running with params: {'learning_rate': 0.08625062199985488, 'max_steps': 3800}
Higher iteration... returning...
Optimization Iteration: 36
Running with params: {'learning_rate': 0.010794255455930882, 'max_steps': 200}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.010794255455930882
Optimization Iteration: 37
Running with params: {'learning_rate': 0.0021188674727015792, 'max_steps': 1800}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.0021188674727015792
Optimization Iteration: 38
Running with params: {'learning_rate': 0.00047320592260434425, 'max_steps': 700}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.00047320592260434425
Optimization Iteration: 39
Running with params: {'learning_rate': 1.2411115813160735e-05, 'max_steps': 1000}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 1.2411115813160735e-05
Optimization Iteration: 40
Running with params: {'learning_rate': 0.032134005315672134, 'max_steps': 700}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.032134005315672134
Optimization Iteration: 41
Running with params: {'learning_rate': 0.09020980876743981, 'max_steps': 1600}
Higher iteration... returning...
Optimization Iteration: 42
Running with params: {'learning_rate': 0.032345255535438176, 'max_steps': 2300}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.032345255535438176
Optimization Iteration: 43
Running with params: {'learning_rate': 0.0018736547106494624, 'max_steps': 1300}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.0018736547106494624
Optimization Iteration: 44
Running with params: {'learning_rate': 0.005753090247272737, 'max_steps': 3400}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.005753090247272737
Optimization Iteration: 45
Running with params: {'learning_rate': 0.5289036045022728, 'max_steps': 200}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.5289036045022728_200
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 18...
Iter 19...
Iter 20...
Iter 21...
Iter 22...
Iter 23...
Iter 24...
Iter 25...
Iter 26...
Iter 27...
Iter 28...
Iter 29...
Timings: Avg: 14.385333333333337, Max: 14.5, Min: 14.07
Passed tests : 0
Failed tests : 30
Half of samples failed, exiting...
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 46
Running with params: {'learning_rate': 0.05852377438620462, 'max_steps': 600}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.05852377438620462
Optimization Iteration: 47
Running with params: {'learning_rate': 0.01780478741884018, 'max_steps': 4800}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.01780478741884018
Optimization Iteration: 48
Running with params: {'learning_rate': 0.008667520453717397, 'max_steps': 200}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.008667520453717397
Optimization Iteration: 49
Running with params: {'learning_rate': 1.1063330349268e-05, 'max_steps': 2400}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 1.1063330349268e-05
Optimization Iteration: 50
Running with params: {'learning_rate': 0.0002732896871952962, 'max_steps': 2600}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.0002732896871952962
Upto iteration 50: {'learning_rate': 0.08166178827568872, 'max_steps': 1200.0}
Optimization Iteration: 51
Running with params: {'learning_rate': 0.8215920622530989, 'max_steps': 800}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.8215920622530989_800
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 18...
Iter 19...
Iter 20...
Iter 21...
Iter 22...
Iter 23...
Iter 24...
Iter 27...
Iter 26...
Iter 28...
Iter 29...
Iter 25...
Timings: Avg: 41.43366666666667, Max: 43.25, Min: 40.11
Passed tests : 0
Failed tests : 30
Half of samples failed, exiting...
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 52
Running with params: {'learning_rate': 0.3817481136682262, 'max_steps': 600}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.3817481136682262_600
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 18...
Iter 19...
Iter 20...
Iter 21...
Iter 22...
Iter 23...
Iter 24...
Iter 25...
Iter 26...
Iter 27...
Iter 28...
Iter 29...
Timings: Avg: 23.00866666666667, Max: 23.27, Min: 22.66
Passed tests : 0
Failed tests : 30
Half of samples failed, exiting...
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 53
Running with params: {'learning_rate': 0.1537293349770863, 'max_steps': 100}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.1537293349770863_100
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 19...
Iter 18...
Iter 20...
Iter 21...
Iter 22...
Iter 24...
Iter 23...
Iter 25...
Iter 26...
Iter 27...
Iter 28...
Iter 29...
Timings: Avg: 12.334, Max: 12.47, Min: 12.01
Passed tests : 0
Failed tests : 30
Half of samples failed, exiting...
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 54
Running with params: {'learning_rate': 0.023750102908003407, 'max_steps': 1700}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.023750102908003407
Optimization Iteration: 55
Running with params: {'learning_rate': 8.412662547483032e-05, 'max_steps': 3100}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 8.412662547483032e-05
Optimization Iteration: 56
Running with params: {'learning_rate': 0.0028243615486945126, 'max_steps': 1400}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.0028243615486945126
Optimization Iteration: 57
Running with params: {'learning_rate': 0.08324411600127668, 'max_steps': 1000}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.08324411600127668_1000
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 20...
Iter 18...
Iter 19...
Iter 21...
Iter 22...
Iter 23...
Iter 24...
Iter 25...
Iter 26...
Iter 27...
Iter 29...
Iter 28...
Timings: Avg: 29.066333333333326, Max: 29.56, Min: 28.419999999999998
Passed tests : 0
Failed tests : 30
Half of samples failed, exiting...
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 58
Running with params: {'learning_rate': 0.5666449355620706, 'max_steps': 1200}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.5666449355620706_1200
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 18...
Iter 19...
Iter 20...
Iter 21...
Iter 22...
Iter 23...
Iter 25...
Iter 24...
Iter 26...
Iter 27...
Iter 29...
Iter 28...
Timings: Avg: 40.668, Max: 41.559999999999995, Min: 39.69
Passed tests : 0
Failed tests : 30
Half of samples failed, exiting...
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 59
Running with params: {'learning_rate': 0.053217646013797866, 'max_steps': 400}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.053217646013797866
Optimization Iteration: 60
Running with params: {'learning_rate': 0.1210005783611458, 'max_steps': 4200}
Higher iteration... returning...
Optimization Iteration: 61
Running with params: {'learning_rate': 0.0016223249592132417, 'max_steps': 1900}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.0016223249592132417
Optimization Iteration: 62
Running with params: {'learning_rate': 0.00535718551393587, 'max_steps': 3600}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.00535718551393587
Optimization Iteration: 63
Running with params: {'learning_rate': 0.36545273864257644, 'max_steps': 500}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.36545273864257644_500
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 18...
Iter 19...
Iter 21...
Iter 20...
Iter 22...
Iter 23...
Iter 24...
Iter 25...
Iter 26...
Iter 27...
Iter 29...
Iter 28...
Timings: Avg: 21.082999999999995, Max: 21.69, Min: 20.720000000000002
Passed tests : 0
Failed tests : 30
Half of samples failed, exiting...
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 64
Running with params: {'learning_rate': 0.1863501985143381, 'max_steps': 1100}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.1863501985143381_1100
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 18...
Iter 20...
Iter 19...
Iter 22...
Iter 21...
Iter 23...
Iter 24...
Iter 26...
Iter 25...
Iter 27...
Iter 29...
Iter 28...
Timings: Avg: 27.064333333333327, Max: 27.48, Min: 26.46
Passed tests : 0
Failed tests : 30
Half of samples failed, exiting...
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 65
Running with params: {'learning_rate': 0.016766303452392425, 'max_steps': 300}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.016766303452392425
Optimization Iteration: 66
Running with params: {'learning_rate': 0.008016304566293724, 'max_steps': 200}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.008016304566293724
Optimization Iteration: 67
Running with params: {'learning_rate': 0.00386486156565681, 'max_steps': 100}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.00386486156565681
Optimization Iteration: 68
Running with params: {'learning_rate': 0.002210079086504404, 'max_steps': 100}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.002210079086504404
Optimization Iteration: 69
Running with params: {'learning_rate': 0.00043469272106565036, 'max_steps': 700}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.00043469272106565036
Optimization Iteration: 70
Running with params: {'learning_rate': 2.238289691485036e-05, 'max_steps': 1900}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 2.238289691485036e-05
Optimization Iteration: 71
Running with params: {'learning_rate': 1.2116331600357225e-05, 'max_steps': 600}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 1.2116331600357225e-05
Optimization Iteration: 72
Running with params: {'learning_rate': 0.00024324279750325778, 'max_steps': 800}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.00024324279750325778
Optimization Iteration: 73
Running with params: {'learning_rate': 0.6500616939206414, 'max_steps': 600}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.6500616939206414_600
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 18...
Iter 19...
Iter 20...
Iter 21...
Iter 23...
Iter 22...
Iter 24...
Iter 25...
Iter 26...
Iter 27...
Iter 28...
Iter 29...
Timings: Avg: 21.104000000000003, Max: 21.330000000000002, Min: 20.71
Passed tests : 0
Failed tests : 30
Half of samples failed, exiting...
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 74
Running with params: {'learning_rate': 0.780159362013104, 'max_steps': 400}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.780159362013104_400
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 19...
Iter 20...
Iter 18...
Iter 21...
Iter 23...
Iter 22...
Iter 24...
Iter 25...
Iter 26...
Iter 27...
Iter 29...
Iter 28...
Timings: Avg: 23.273333333333326, Max: 23.549999999999997, Min: 22.66
Passed tests : 30
Failed tests : 0
Converged: True
Convergence score: 0.0
Evaluating 30 values out of 30
Overall-timings: Avg: 23.273333333333326, Max: 23.549999999999997, Min: 22.66
Variance (0.0) too small, using delta distribution
Variance (1.232595164407831e-32) too small, using delta distribution
Probability of fail (non-zero): 1.0
Exceeding max probability of failure: 1.0
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 75
Running with params: {'learning_rate': 0.2035351774315002, 'max_steps': 300}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.2035351774315002_300
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 18...
Iter 19...
Iter 20...
Iter 21...
Iter 22...
Iter 23...
Iter 25...
Iter 26...
Iter 27...
Iter 24...
Iter 29...
Iter 28...
Timings: Avg: 15.771666666666667, Max: 15.92, Min: 15.450000000000001
Passed tests : 0
Failed tests : 30
Half of samples failed, exiting...
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 76
Running with params: {'learning_rate': 0.024600807913235035, 'max_steps': 1500}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.024600807913235035
Optimization Iteration: 77
Running with params: {'learning_rate': 5.791053166466742e-05, 'max_steps': 1700}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 5.791053166466742e-05
Optimization Iteration: 78
Running with params: {'learning_rate': 0.00010776415889419055, 'max_steps': 2200}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.00010776415889419055
Optimization Iteration: 79
Running with params: {'learning_rate': 1.8325601183929825e-05, 'max_steps': 3000}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 1.8325601183929825e-05
Optimization Iteration: 80
Running with params: {'learning_rate': 0.0011646983567140648, 'max_steps': 1000}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.0011646983567140648
Optimization Iteration: 81
Running with params: {'learning_rate': 0.07483112037932352, 'max_steps': 1200}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.07483112037932352_1200
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 19...
Iter 18...
Iter 20...
Iter 21...
Iter 22...
Iter 23...
Iter 24...
Iter 25...
Iter 26...
Iter 27...
Iter 28...
Iter 29...
Timings: Avg: 26.95, Max: 27.31, Min: 26.36
Passed tests : 0
Failed tests : 30
Half of samples failed, exiting...
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 82
Running with params: {'learning_rate': 0.03693239813379697, 'max_steps': 900}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.03693239813379697
Optimization Iteration: 83
Running with params: {'learning_rate': 0.04892262786363327, 'max_steps': 400}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.04892262786363327
Optimization Iteration: 84
Running with params: {'learning_rate': 0.2976918992280739, 'max_steps': 4200}
Higher iteration... returning...
Optimization Iteration: 85
Running with params: {'learning_rate': 0.001576755547009052, 'max_steps': 4400}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.001576755547009052
Optimization Iteration: 86
Running with params: {'learning_rate': 0.0006762393514523321, 'max_steps': 2800}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.0006762393514523321
Optimization Iteration: 87
Running with params: {'learning_rate': 0.005790581374952268, 'max_steps': 3500}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.005790581374952268
Optimization Iteration: 88
Running with params: {'learning_rate': 0.013967181778738177, 'max_steps': 300}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.013967181778738177
Optimization Iteration: 89
Running with params: {'learning_rate': 0.1075626859614463, 'max_steps': 500}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.1075626859614463_500
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 14...
Iter 15...
Iter 16...
Iter 17...
Iter 18...
Iter 19...
Iter 20...
Iter 21...
Iter 23...
Iter 22...
Iter 24...
Iter 25...
Iter 26...
Iter 28...
Iter 29...
Iter 27...
Timings: Avg: 20.39166666666667, Max: 20.57, Min: 19.99
Passed tests : 30
Failed tests : 0
Converged: True
Convergence score: 0.0
Evaluating 30 values out of 30
Overall-timings: Avg: 20.39166666666667, Max: 20.57, Min: 19.99
Variance (0.0) too small, using delta distribution
Variance (1.232595164407831e-32) too small, using delta distribution
Probability of fail (non-zero): 1.0
Exceeding max probability of failure: 1.0
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 90
Running with params: {'learning_rate': 0.4184357040774584, 'max_steps': 500}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.4184357040774584_500
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 15...
Iter 14...
Iter 16...
Iter 18...
Iter 19...
Iter 20...
Iter 21...
Iter 17...
Iter 22...
Iter 23...
Iter 24...
Iter 25...
Iter 28...
Iter 27...
Iter 29...
Iter 26...
Timings: Avg: 19.53166666666667, Max: 19.77, Min: 19.18
Passed tests : 0
Failed tests : 30
Half of samples failed, exiting...
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 91
Running with params: {'learning_rate': 0.16332859226775093, 'max_steps': 200}
Logdir: /mnt/batch/tasks/workitems/opt1/job-1/Task_ml-agents/wd/borntobeflaky/tool/logs/optim_1597795256_ml-agents/run_1597795256/assert_62470885_0.16332859226775093_200
Launching 30 jobs, 30 in parallel
Iter 0...
Iter 1...
Iter 2...
Iter 3...
Iter 4...
Iter 5...
Iter 6...
Iter 7...
Iter 8...
Iter 9...
Iter 10...
Iter 11...
Iter 12...
Iter 13...
Iter 15...
Iter 14...
Iter 16...
Iter 17...
Iter 18...
Iter 19...
Iter 20...
Iter 21...
Iter 23...
Iter 22...
Iter 24...
Iter 27...
Iter 28...
Iter 25...
Iter 29...
Iter 26...
Timings: Avg: 14.424999999999995, Max: 14.55, Min: 14.110000000000001
Passed tests : 0
Failed tests : 30
Half of samples failed, exiting...
All-Passed: False
Probabilty of failure: 1.0
Runtime: 10000.0
Score: 3.4028234663852886e+38
Best-score: 32.281
Best-param: {'learning_rate': 0.08166178827568872, 'max_steps': 1200}
Optimization Iteration: 92
Running with params: {'learning_rate': 0.009565723364244461, 'max_steps': 200}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.009565723364244461
Optimization Iteration: 93
Running with params: {'learning_rate': 0.003731607701797786, 'max_steps': 100}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.003731607701797786
Optimization Iteration: 94
Running with params: {'learning_rate': 0.003271336571883532, 'max_steps': 100}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.003271336571883532
Optimization Iteration: 95
Running with params: {'learning_rate': 0.002644245562339519, 'max_steps': 100}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.002644245562339519
Optimization Iteration: 96
Running with params: {'learning_rate': 0.00014484839054383232, 'max_steps': 700}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.00014484839054383232
Optimization Iteration: 97
Running with params: {'learning_rate': 2.21199476700477e-05, 'max_steps': 1400}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 2.21199476700477e-05
Optimization Iteration: 98
Running with params: {'learning_rate': 4.1994009070043224e-05, 'max_steps': 2600}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 4.1994009070043224e-05
Optimization Iteration: 99
Running with params: {'learning_rate': 1.4781188306529676e-05, 'max_steps': 900}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 1.4781188306529676e-05
Optimization Iteration: 100
Running with params: {'learning_rate': 0.00025657544058422594, 'max_steps': 800}
Lower learning rate.. returning... Best: 0.08166178827568872, Proposed: 0.00025657544058422594
Upto iteration 100: {'learning_rate': 0.08166178827568872, 'max_steps': 1200.0}
Breaking...
{'learning_rate': 0.08166178827568872, 'max_steps': 1200.0}
Best score: 32.281
Repeated params: 0
Trials: 101
Best param {'learning_rate': 0.08166178827568872, 'max_steps': 1200.0}
Reduction: 73.92852912354759%
Speedup: 3.8356102144708455x
Optimizer time: 709.6300411224365
