Bronion's picture
Huggy
e0c5631
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3956167697906494,
"min": 1.3956167697906494,
"max": 1.4249565601348877,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 67187.78125,
"min": 67187.78125,
"max": 77409.203125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 106.58279569892473,
"min": 80.1590909090909,
"max": 398.09448818897636,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49561.0,
"min": 48924.0,
"max": 50558.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999941.0,
"min": 49991.0,
"max": 1999941.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999941.0,
"min": 49991.0,
"max": 1999941.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4577250480651855,
"min": 0.1512860506772995,
"max": 2.5088586807250977,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1142.8421630859375,
"min": 19.062042236328125,
"max": 1515.2545166015625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7054387059263005,
"min": 1.9207808730148135,
"max": 3.965199989351359,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1723.0289982557297,
"min": 242.01838999986649,
"max": 2356.0787888765335,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7054387059263005,
"min": 1.9207808730148135,
"max": 3.965199989351359,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1723.0289982557297,
"min": 242.01838999986649,
"max": 2356.0787888765335,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014692564402260662,
"min": 0.01332546478176179,
"max": 0.02152645689525848,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04407769320678199,
"min": 0.02665092956352358,
"max": 0.06457937068577545,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04938545881046189,
"min": 0.021683009620755908,
"max": 0.07642383836209773,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14815637643138568,
"min": 0.043366019241511816,
"max": 0.18605702345569927,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4120488626833295e-06,
"min": 3.4120488626833295e-06,
"max": 0.0002953470765509749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0236146588049989e-05,
"min": 1.0236146588049989e-05,
"max": 0.0008439199686933501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10113731666666664,
"min": 0.10113731666666664,
"max": 0.19844902500000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30341194999999993,
"min": 0.20743970000000003,
"max": 0.5813066500000003,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.675210166666662e-05,
"min": 6.675210166666662e-05,
"max": 0.004922606347499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020025630499999987,
"min": 0.00020025630499999987,
"max": 0.014067201835000001,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1687927948",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1687930532"
},
"total": 2584.054942414,
"count": 1,
"self": 0.436555313000099,
"children": {
"run_training.setup": {
"total": 0.042821485999979814,
"count": 1,
"self": 0.042821485999979814
},
"TrainerController.start_learning": {
"total": 2583.575565615,
"count": 1,
"self": 4.607878406856798,
"children": {
"TrainerController._reset_env": {
"total": 5.451861347999966,
"count": 1,
"self": 5.451861347999966
},
"TrainerController.advance": {
"total": 2573.383775406143,
"count": 232547,
"self": 4.932831163136598,
"children": {
"env_step": {
"total": 2017.6856614189144,
"count": 232547,
"self": 1696.7529624550798,
"children": {
"SubprocessEnvManager._take_step": {
"total": 317.85202644494314,
"count": 232547,
"self": 17.847236332941065,
"children": {
"TorchPolicy.evaluate": {
"total": 300.00479011200207,
"count": 222874,
"self": 300.00479011200207
}
}
},
"workers": {
"total": 3.080672518891447,
"count": 232547,
"self": 0.0,
"children": {
"worker_root": {
"total": 2575.3262565809205,
"count": 232547,
"is_parallel": true,
"self": 1192.540474253813,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009750100000474049,
"count": 1,
"is_parallel": true,
"self": 0.0002629370001159259,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000712072999931479,
"count": 2,
"is_parallel": true,
"self": 0.000712072999931479
}
}
},
"UnityEnvironment.step": {
"total": 0.07266571500008467,
"count": 1,
"is_parallel": true,
"self": 0.0003842310001118676,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002462789999526649,
"count": 1,
"is_parallel": true,
"self": 0.0002462789999526649
},
"communicator.exchange": {
"total": 0.0711230430000569,
"count": 1,
"is_parallel": true,
"self": 0.0711230430000569
},
"steps_from_proto": {
"total": 0.0009121619999632458,
"count": 1,
"is_parallel": true,
"self": 0.00028434199998628173,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000627819999976964,
"count": 2,
"is_parallel": true,
"self": 0.000627819999976964
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1382.7857823271074,
"count": 232546,
"is_parallel": true,
"self": 40.570423683112494,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.49238047698054,
"count": 232546,
"is_parallel": true,
"self": 86.49238047698054
},
"communicator.exchange": {
"total": 1155.251521214012,
"count": 232546,
"is_parallel": true,
"self": 1155.251521214012
},
"steps_from_proto": {
"total": 100.47145695300242,
"count": 232546,
"is_parallel": true,
"self": 38.02463467386053,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.446822279141884,
"count": 465092,
"is_parallel": true,
"self": 62.446822279141884
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 550.7652828240921,
"count": 232547,
"self": 7.063806978151206,
"children": {
"process_trajectory": {
"total": 147.00283120593872,
"count": 232547,
"self": 145.4955224719389,
"children": {
"RLTrainer._checkpoint": {
"total": 1.507308733999821,
"count": 10,
"self": 1.507308733999821
}
}
},
"_update_policy": {
"total": 396.69864464000216,
"count": 97,
"self": 334.91506876000915,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.78357587999301,
"count": 2910,
"self": 61.78357587999301
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0590001693344675e-06,
"count": 1,
"self": 1.0590001693344675e-06
},
"TrainerController._save_models": {
"total": 0.13204939500019464,
"count": 1,
"self": 0.0021962410000924137,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12985315400010222,
"count": 1,
"self": 0.12985315400010222
}
}
}
}
}
}
}