|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.3605869710445404, |
|
"min": 0.3400476276874542, |
|
"max": 1.458526372909546, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 10731.068359375, |
|
"min": 10190.546875, |
|
"max": 44245.85546875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989873.0, |
|
"min": 29952.0, |
|
"max": 989873.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989873.0, |
|
"min": 29952.0, |
|
"max": 989873.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.2841116786003113, |
|
"min": -0.11605717241764069, |
|
"max": 0.3512202799320221, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 73.86903381347656, |
|
"min": -28.201892852783203, |
|
"max": 91.31727600097656, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.027897167950868607, |
|
"min": -0.004961548838764429, |
|
"max": 0.3119995594024658, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 7.253263473510742, |
|
"min": -1.257606029510498, |
|
"max": 75.19189453125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06909028818370731, |
|
"min": 0.06531761152398913, |
|
"max": 0.07433437728988272, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9672640345719024, |
|
"min": 0.5203406410291791, |
|
"max": 1.0356888846246646, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.012670259417766927, |
|
"min": 6.385160697513942e-05, |
|
"max": 0.012670259417766927, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.17738363184873698, |
|
"min": 0.0008300708906768125, |
|
"max": 0.17738363184873698, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.543661771192856e-06, |
|
"min": 7.543661771192856e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010561126479669998, |
|
"min": 0.00010561126479669998, |
|
"max": 0.0031393613535463, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10251452142857141, |
|
"min": 0.10251452142857141, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4352032999999997, |
|
"min": 1.3886848, |
|
"max": 2.3464537, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002612006907142857, |
|
"min": 0.0002612006907142857, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0036568096699999995, |
|
"min": 0.0036568096699999995, |
|
"max": 0.10467072462999999, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.009585014544427395, |
|
"min": 0.009585014544427395, |
|
"max": 0.3893595337867737, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.13419020175933838, |
|
"min": 0.13419020175933838, |
|
"max": 2.7255167961120605, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 521.5357142857143, |
|
"min": 521.5357142857143, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29206.0, |
|
"min": 15984.0, |
|
"max": 32372.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.2641142514933432, |
|
"min": -1.0000000521540642, |
|
"max": 1.2641142514933432, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 70.79039808362722, |
|
"min": -31.998401656746864, |
|
"max": 70.79039808362722, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.2641142514933432, |
|
"min": -1.0000000521540642, |
|
"max": 1.2641142514933432, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 70.79039808362722, |
|
"min": -31.998401656746864, |
|
"max": 70.79039808362722, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.052050619646122086, |
|
"min": 0.052050619646122086, |
|
"max": 7.829729118384421, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.914834700182837, |
|
"min": 2.914834700182837, |
|
"max": 125.27566589415073, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1683885667", |
|
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", |
|
"mlagents_version": "0.31.0.dev0", |
|
"mlagents_envs_version": "0.31.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.11.0+cu102", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1683887676" |
|
}, |
|
"total": 2009.0701628230004, |
|
"count": 1, |
|
"self": 1.0030176630002643, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.056257677000303374, |
|
"count": 1, |
|
"self": 0.056257677000303374 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2008.0108874829998, |
|
"count": 1, |
|
"self": 1.2968964599372157, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 4.69990780299986, |
|
"count": 1, |
|
"self": 4.69990780299986 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2001.869059152063, |
|
"count": 63293, |
|
"self": 1.3383174540635991, |
|
"children": { |
|
"env_step": { |
|
"total": 1366.1776765859795, |
|
"count": 63293, |
|
"self": 1257.7292131820864, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 107.65524394289059, |
|
"count": 63293, |
|
"self": 4.7127226299153335, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 102.94252131297526, |
|
"count": 62560, |
|
"self": 102.94252131297526 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.7932194610025363, |
|
"count": 63293, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2003.0740155279987, |
|
"count": 63293, |
|
"is_parallel": true, |
|
"self": 855.2044149290041, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.002719808000165358, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007502739999836194, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0019695340001817385, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0019695340001817385 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04743323899992902, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005395749999479449, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004623479999281699, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004623479999281699 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04468808399997215, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04468808399997215 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0017432320000807522, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00035821199981000973, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013850200002707425, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013850200002707425 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1147.8696005989946, |
|
"count": 63292, |
|
"is_parallel": true, |
|
"self": 31.192967495954235, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.526004632028616, |
|
"count": 63292, |
|
"is_parallel": true, |
|
"self": 22.526004632028616 |
|
}, |
|
"communicator.exchange": { |
|
"total": 998.0063941910448, |
|
"count": 63292, |
|
"is_parallel": true, |
|
"self": 998.0063941910448 |
|
}, |
|
"steps_from_proto": { |
|
"total": 96.1442342799669, |
|
"count": 63292, |
|
"is_parallel": true, |
|
"self": 19.33867356187511, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 76.80556071809178, |
|
"count": 506336, |
|
"is_parallel": true, |
|
"self": 76.80556071809178 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 634.35306511202, |
|
"count": 63293, |
|
"self": 2.3382927920633847, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 105.02987556895368, |
|
"count": 63293, |
|
"self": 104.77374332895306, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.25613224000062473, |
|
"count": 2, |
|
"self": 0.25613224000062473 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 526.9848967510029, |
|
"count": 435, |
|
"self": 338.41633015003026, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 188.56856660097264, |
|
"count": 22902, |
|
"self": 188.56856660097264 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.1310003174003214e-06, |
|
"count": 1, |
|
"self": 1.1310003174003214e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.14502293699933944, |
|
"count": 1, |
|
"self": 0.0018920349994004937, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.14313090199993894, |
|
"count": 1, |
|
"self": 0.14313090199993894 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |