|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SpaceMan.Policy.Entropy.mean": { |
|
"value": 1.4396039247512817, |
|
"min": 1.404689073562622, |
|
"max": 1.449188232421875, |
|
"count": 300 |
|
}, |
|
"SpaceMan.Policy.Entropy.sum": { |
|
"value": 14423.3916015625, |
|
"min": 13927.4931640625, |
|
"max": 14607.111328125, |
|
"count": 300 |
|
}, |
|
"SpaceMan.Step.mean": { |
|
"value": 2999989.0, |
|
"min": 9909.0, |
|
"max": 2999989.0, |
|
"count": 300 |
|
}, |
|
"SpaceMan.Step.sum": { |
|
"value": 2999989.0, |
|
"min": 9909.0, |
|
"max": 2999989.0, |
|
"count": 300 |
|
}, |
|
"SpaceMan.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 5.108259677886963, |
|
"min": -0.0456768199801445, |
|
"max": 5.308773517608643, |
|
"count": 300 |
|
}, |
|
"SpaceMan.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 541.4755249023438, |
|
"min": -4.933096408843994, |
|
"max": 557.4212036132812, |
|
"count": 300 |
|
}, |
|
"SpaceMan.Environment.EpisodeLength.mean": { |
|
"value": 743.2142857142857, |
|
"min": 239.0, |
|
"max": 1272.4285714285713, |
|
"count": 300 |
|
}, |
|
"SpaceMan.Environment.EpisodeLength.sum": { |
|
"value": 10405.0, |
|
"min": 8081.0, |
|
"max": 12535.0, |
|
"count": 300 |
|
}, |
|
"SpaceMan.Environment.CumulativeReward.mean": { |
|
"value": 58.78126232440655, |
|
"min": 10.89677467800322, |
|
"max": 105.08675193786621, |
|
"count": 300 |
|
}, |
|
"SpaceMan.Environment.CumulativeReward.sum": { |
|
"value": 764.1564102172852, |
|
"min": 457.66453647613525, |
|
"max": 936.7664852142334, |
|
"count": 300 |
|
}, |
|
"SpaceMan.Policy.ExtrinsicReward.mean": { |
|
"value": 58.78126232440655, |
|
"min": 10.89677467800322, |
|
"max": 105.08675193786621, |
|
"count": 300 |
|
}, |
|
"SpaceMan.Policy.ExtrinsicReward.sum": { |
|
"value": 764.1564102172852, |
|
"min": 457.66453647613525, |
|
"max": 936.7664852142334, |
|
"count": 300 |
|
}, |
|
"SpaceMan.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 300 |
|
}, |
|
"SpaceMan.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 300 |
|
}, |
|
"SpaceMan.Losses.PolicyLoss.mean": { |
|
"value": 0.017731686183484273, |
|
"min": 0.017370412978576496, |
|
"max": 0.018258020761189982, |
|
"count": 14 |
|
}, |
|
"SpaceMan.Losses.PolicyLoss.sum": { |
|
"value": 0.017731686183484273, |
|
"min": 0.017370412978576496, |
|
"max": 0.018258020761189982, |
|
"count": 14 |
|
}, |
|
"SpaceMan.Losses.ValueLoss.mean": { |
|
"value": 1.5500787984132767, |
|
"min": 0.6227473085820675, |
|
"max": 1.6574717750549317, |
|
"count": 14 |
|
}, |
|
"SpaceMan.Losses.ValueLoss.sum": { |
|
"value": 1.5500787984132767, |
|
"min": 0.6227473085820675, |
|
"max": 1.6574717750549317, |
|
"count": 14 |
|
}, |
|
"SpaceMan.Policy.LearningRate.mean": { |
|
"value": 1.3200195599966665e-05, |
|
"min": 1.3200195599966665e-05, |
|
"max": 0.0002795162068279333, |
|
"count": 14 |
|
}, |
|
"SpaceMan.Policy.LearningRate.sum": { |
|
"value": 1.3200195599966665e-05, |
|
"min": 1.3200195599966665e-05, |
|
"max": 0.0002795162068279333, |
|
"count": 14 |
|
}, |
|
"SpaceMan.Policy.Epsilon.mean": { |
|
"value": 0.10440003333333331, |
|
"min": 0.10440003333333331, |
|
"max": 0.19317206666666664, |
|
"count": 14 |
|
}, |
|
"SpaceMan.Policy.Epsilon.sum": { |
|
"value": 0.10440003333333331, |
|
"min": 0.10440003333333331, |
|
"max": 0.19317206666666664, |
|
"count": 14 |
|
}, |
|
"SpaceMan.Policy.Beta.mean": { |
|
"value": 0.005, |
|
"min": 0.005, |
|
"max": 0.005, |
|
"count": 14 |
|
}, |
|
"SpaceMan.Policy.Beta.sum": { |
|
"value": 0.005, |
|
"min": 0.005, |
|
"max": 0.005, |
|
"count": 14 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1708233795", |
|
"python_version": "3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]", |
|
"command_line_arguments": "C:\\Users\\marko\\Documents\\UNITY\\ML-Agents\\.venv\\Scripts\\mlagents-learn config/ppo/SpaceManConfig.yaml --run-id=SpaceMan", |
|
"mlagents_version": "1.0.0", |
|
"mlagents_envs_version": "1.0.0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.13.1+cu117", |
|
"numpy_version": "1.23.4", |
|
"end_time_seconds": "1708251695" |
|
}, |
|
"total": 17899.673288199992, |
|
"count": 1, |
|
"self": 0.050844899960793555, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.094327200029511, |
|
"count": 1, |
|
"self": 0.094327200029511 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 17899.528116100002, |
|
"count": 1, |
|
"self": 48.87804145150585, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 20.616248000005726, |
|
"count": 1, |
|
"self": 20.616248000005726 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 17829.817165548448, |
|
"count": 3007047, |
|
"self": 43.271958130644634, |
|
"children": { |
|
"env_step": { |
|
"total": 15947.844941709773, |
|
"count": 3007047, |
|
"self": 8307.44479442708, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 7608.474235826696, |
|
"count": 3007047, |
|
"self": 144.90336746699177, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 7463.570868359704, |
|
"count": 3000019, |
|
"self": 7463.570868359704 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 31.925911455997266, |
|
"count": 3007047, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 17826.03124869382, |
|
"count": 3007047, |
|
"is_parallel": true, |
|
"self": 11705.28407783201, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0030157999717630446, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00010429997928440571, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.002911499992478639, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.002911499992478639 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 6120.744155061839, |
|
"count": 3007047, |
|
"is_parallel": true, |
|
"self": 185.63163686619373, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 148.9114509843639, |
|
"count": 3007047, |
|
"is_parallel": true, |
|
"self": 148.9114509843639 |
|
}, |
|
"communicator.exchange": { |
|
"total": 5352.722329935117, |
|
"count": 3007047, |
|
"is_parallel": true, |
|
"self": 5352.722329935117 |
|
}, |
|
"steps_from_proto": { |
|
"total": 433.4787372761639, |
|
"count": 3007047, |
|
"is_parallel": true, |
|
"self": 200.26946144725662, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 233.20927582890727, |
|
"count": 6014094, |
|
"is_parallel": true, |
|
"self": 233.20927582890727 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1838.7002657080302, |
|
"count": 3007047, |
|
"self": 52.23635603673756, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 292.4972032713704, |
|
"count": 3007047, |
|
"self": 290.8138325713808, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 1.6833706999896094, |
|
"count": 6, |
|
"self": 1.6833706999896094 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1493.9667063999223, |
|
"count": 14, |
|
"self": 1025.7034898959682, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 468.263216503954, |
|
"count": 14000, |
|
"self": 468.263216503954 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.200009137392044e-06, |
|
"count": 1, |
|
"self": 1.200009137392044e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.2166599000338465, |
|
"count": 1, |
|
"self": 0.01178780006011948, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.20487209997372702, |
|
"count": 1, |
|
"self": 0.20487209997372702 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |