|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.6822641491889954, |
|
"min": 0.5891025066375732, |
|
"max": 1.3654537200927734, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 20653.5, |
|
"min": 17644.798828125, |
|
"max": 41422.40234375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989958.0, |
|
"min": 29952.0, |
|
"max": 989958.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989958.0, |
|
"min": 29952.0, |
|
"max": 989958.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.18176929652690887, |
|
"min": -0.1126280426979065, |
|
"max": 0.18176929652690887, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 46.169403076171875, |
|
"min": -27.14335823059082, |
|
"max": 46.19596862792969, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.056453533470630646, |
|
"min": -0.056453533470630646, |
|
"max": 1.6944763660430908, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -14.339197158813477, |
|
"min": -14.339197158813477, |
|
"max": 408.3688049316406, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.030586998219535283, |
|
"min": 0.028564181747025855, |
|
"max": 0.03775057013441181, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.42821797507349396, |
|
"min": 0.2642539909408827, |
|
"max": 0.49323315965011716, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.012776392837016221, |
|
"min": 0.0002518038248429851, |
|
"max": 0.057195161356825105, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.1788694997182271, |
|
"min": 0.0035252535478017912, |
|
"max": 0.4003661294977757, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.577711759842856e-06, |
|
"min": 7.577711759842856e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010608796463779998, |
|
"min": 0.00010608796463779998, |
|
"max": 0.003634963988345399, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10252587142857143, |
|
"min": 0.10252587142857143, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4353622000000001, |
|
"min": 1.3886848, |
|
"max": 2.6116545999999996, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00026233455571428576, |
|
"min": 0.00026233455571428576, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0036726837800000007, |
|
"min": 0.0036726837800000007, |
|
"max": 0.12118429453999999, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.04017286375164986, |
|
"min": 0.04017286375164986, |
|
"max": 2.141740560531616, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.5624200701713562, |
|
"min": 0.5624200701713562, |
|
"max": 14.99218463897705, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 602.0204081632653, |
|
"min": 602.0204081632653, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29499.0, |
|
"min": 15984.0, |
|
"max": 32777.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 0.7855183404623246, |
|
"min": -1.0000000521540642, |
|
"max": 0.9778448729490747, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 38.490398682653904, |
|
"min": -31.98920165002346, |
|
"max": 47.91439877450466, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 0.7855183404623246, |
|
"min": -1.0000000521540642, |
|
"max": 0.9778448729490747, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 38.490398682653904, |
|
"min": -31.98920165002346, |
|
"max": 47.91439877450466, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.2454499905425295, |
|
"min": 0.2454499905425295, |
|
"max": 21.29544547945261, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 12.027049536583945, |
|
"min": 12.027049536583945, |
|
"max": 602.9911260008812, |
|
"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": "1674008596", |
|
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0", |
|
"mlagents_envs_version": "0.29.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.8.1+cu102", |
|
"numpy_version": "1.21.6", |
|
"end_time_seconds": "1674010312" |
|
}, |
|
"total": 1716.071354434, |
|
"count": 1, |
|
"self": 0.43023786299977473, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10233200200013925, |
|
"count": 1, |
|
"self": 0.10233200200013925 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1715.5387845690002, |
|
"count": 1, |
|
"self": 1.1270634289303416, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.113788699999986, |
|
"count": 1, |
|
"self": 6.113788699999986 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1708.2191367230698, |
|
"count": 63334, |
|
"self": 1.1861210850411226, |
|
"children": { |
|
"env_step": { |
|
"total": 1225.327911995001, |
|
"count": 63334, |
|
"self": 1127.0745705079764, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 97.574441635016, |
|
"count": 63334, |
|
"self": 4.038260728955947, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 93.53618090606005, |
|
"count": 62573, |
|
"self": 31.45784248506834, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 62.07833842099171, |
|
"count": 62573, |
|
"self": 62.07833842099171 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.6788998520084988, |
|
"count": 63334, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1711.835423735028, |
|
"count": 63334, |
|
"is_parallel": true, |
|
"self": 675.5682362690407, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0016226479999659205, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005872860001545632, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0010353619998113572, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0010353619998113572 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04576840599997922, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004961610000009387, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004521519999798329, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004521519999798329 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04319695300000603, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04319695300000603 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016231399999924179, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004488300000957679, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.00117430999989665, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.00117430999989665 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1036.2671874659873, |
|
"count": 63333, |
|
"is_parallel": true, |
|
"self": 26.98367164293427, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 21.2944288070305, |
|
"count": 63333, |
|
"is_parallel": true, |
|
"self": 21.2944288070305 |
|
}, |
|
"communicator.exchange": { |
|
"total": 894.3264765739971, |
|
"count": 63333, |
|
"is_parallel": true, |
|
"self": 894.3264765739971 |
|
}, |
|
"steps_from_proto": { |
|
"total": 93.66261044202543, |
|
"count": 63333, |
|
"is_parallel": true, |
|
"self": 20.14915582816684, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 73.51345461385858, |
|
"count": 506664, |
|
"is_parallel": true, |
|
"self": 73.51345461385858 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 481.70510364302777, |
|
"count": 63334, |
|
"self": 2.1311197200514016, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 138.4654726979768, |
|
"count": 63334, |
|
"self": 138.28079417097683, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.18467852699996, |
|
"count": 2, |
|
"self": 0.18467852699996 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 341.1085112249996, |
|
"count": 453, |
|
"self": 180.02216890600357, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 161.086342318996, |
|
"count": 5616, |
|
"self": 161.086342318996 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0099997780343983e-06, |
|
"count": 1, |
|
"self": 1.0099997780343983e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.07879470700027014, |
|
"count": 1, |
|
"self": 0.0013026430005993461, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.07749206399967079, |
|
"count": 1, |
|
"self": 0.07749206399967079 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |