|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.17482811212539673, |
|
"min": 0.17330242693424225, |
|
"max": 1.4507393836975098, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 5242.0458984375, |
|
"min": 5151.9345703125, |
|
"max": 44009.62890625, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999924.0, |
|
"min": 29912.0, |
|
"max": 2999924.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999924.0, |
|
"min": 29912.0, |
|
"max": 2999924.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.8132672905921936, |
|
"min": -0.21639706194400787, |
|
"max": 0.8132672905921936, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 242.35365295410156, |
|
"min": -51.286102294921875, |
|
"max": 242.35365295410156, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.010181977413594723, |
|
"min": -0.025289621204137802, |
|
"max": 0.303748220205307, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 3.034229278564453, |
|
"min": -7.00522518157959, |
|
"max": 73.20332336425781, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06837959499874463, |
|
"min": 0.06452693229667379, |
|
"max": 0.07303278170533242, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0256939249811694, |
|
"min": 0.4836235476113139, |
|
"max": 1.093776802693302, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.0130653168740941, |
|
"min": 0.0005115327173492487, |
|
"max": 0.015645201730637107, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.1959797531114115, |
|
"min": 0.005115327173492487, |
|
"max": 0.22900681754040042, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.5169661610444478e-06, |
|
"min": 1.5169661610444478e-06, |
|
"max": 0.00029841154338662855, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.2754492415666716e-05, |
|
"min": 2.2754492415666716e-05, |
|
"max": 0.003892477302507633, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10050562222222222, |
|
"min": 0.10050562222222222, |
|
"max": 0.1994705142857143, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5075843333333332, |
|
"min": 1.3962936000000001, |
|
"max": 2.797492366666667, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 6.05116600000001e-05, |
|
"min": 6.05116600000001e-05, |
|
"max": 0.009947104377142857, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0009076749000000014, |
|
"min": 0.0009076749000000014, |
|
"max": 0.12976948743000002, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.004741171840578318, |
|
"min": 0.004624335560947657, |
|
"max": 0.44086360931396484, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.0711175799369812, |
|
"min": 0.06474069505929947, |
|
"max": 3.086045265197754, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 231.9291338582677, |
|
"min": 231.9291338582677, |
|
"max": 998.78125, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29455.0, |
|
"min": 16711.0, |
|
"max": 33014.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7365653442116233, |
|
"min": -0.9372500504832715, |
|
"max": 1.7610959882736206, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 220.54379871487617, |
|
"min": -29.992001615464687, |
|
"max": 221.33199779689312, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7365653442116233, |
|
"min": -0.9372500504832715, |
|
"max": 1.7610959882736206, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 220.54379871487617, |
|
"min": -29.992001615464687, |
|
"max": 221.33199779689312, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.011310607960136464, |
|
"min": 0.011310607960136464, |
|
"max": 8.401019156855696, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 1.436447210937331, |
|
"min": 1.4348511838979903, |
|
"max": 142.81732566654682, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1706589002", |
|
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics --force", |
|
"mlagents_version": "1.1.0.dev0", |
|
"mlagents_envs_version": "1.1.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "2.1.2+cu121", |
|
"numpy_version": "1.23.5", |
|
"end_time_seconds": "1706595885" |
|
}, |
|
"total": 6883.719659685, |
|
"count": 1, |
|
"self": 0.5645091610003874, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.07568099499997061, |
|
"count": 1, |
|
"self": 0.07568099499997061 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 6883.079469529, |
|
"count": 1, |
|
"self": 4.229469305236307, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 3.3904160289999936, |
|
"count": 1, |
|
"self": 3.3904160289999936 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 6875.370577205763, |
|
"count": 193918, |
|
"self": 4.462017299530999, |
|
"children": { |
|
"env_step": { |
|
"total": 4958.729628320185, |
|
"count": 193918, |
|
"self": 4564.427026540247, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 391.6837921569845, |
|
"count": 193918, |
|
"self": 14.520287364885917, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 377.1635047920986, |
|
"count": 187549, |
|
"self": 377.1635047920986 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.6188096229529947, |
|
"count": 193918, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 6867.824345605776, |
|
"count": 193918, |
|
"is_parallel": true, |
|
"self": 2657.9586808818176, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.004735423000056471, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0035325910001802185, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012028319998762527, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012028319998762527 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.08721992300002057, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006619289999889588, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004915220000611953, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004915220000611953 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.08447703399997408, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.08447703399997408 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015894379999963348, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00033306799980437063, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012563700001919642, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012563700001919642 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 4209.865664723959, |
|
"count": 193917, |
|
"is_parallel": true, |
|
"self": 108.53745355305182, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 74.26488092700095, |
|
"count": 193917, |
|
"is_parallel": true, |
|
"self": 74.26488092700095 |
|
}, |
|
"communicator.exchange": { |
|
"total": 3726.0994106950116, |
|
"count": 193917, |
|
"is_parallel": true, |
|
"self": 3726.0994106950116 |
|
}, |
|
"steps_from_proto": { |
|
"total": 300.96391954889475, |
|
"count": 193917, |
|
"is_parallel": true, |
|
"self": 60.51398081750642, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 240.44993873138833, |
|
"count": 1551336, |
|
"is_parallel": true, |
|
"self": 240.44993873138833 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1912.178931586047, |
|
"count": 193918, |
|
"self": 8.843336463985452, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 389.53699774305335, |
|
"count": 193918, |
|
"self": 388.9952704260537, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.5417273169996406, |
|
"count": 6, |
|
"self": 0.5417273169996406 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1513.7985973790082, |
|
"count": 1390, |
|
"self": 892.9627504329926, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 620.8358469460156, |
|
"count": 68442, |
|
"self": 620.8358469460156 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.599998520570807e-07, |
|
"count": 1, |
|
"self": 9.599998520570807e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08900602900030208, |
|
"count": 1, |
|
"self": 0.0017166970001198933, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08728933200018218, |
|
"count": 1, |
|
"self": 0.08728933200018218 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |