ltaylor48's picture
First Push
708e737 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9713780283927917,
"min": 0.9713780283927917,
"max": 2.81943416595459,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9231.9765625,
"min": 9231.9765625,
"max": 28780.783203125,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.495878219604492,
"min": 0.2977248430252075,
"max": 12.495878219604492,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2436.6962890625,
"min": 57.75862121582031,
"max": 2517.10595703125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06079961337384114,
"min": 0.06079961337384114,
"max": 0.07571981208713943,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24319845349536456,
"min": 0.24319845349536456,
"max": 0.3648553576135515,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20195085474965618,
"min": 0.13742524597054237,
"max": 0.27922257243418225,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8078034189986247,
"min": 0.5497009838821695,
"max": 1.3961128621709111,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.886363636363637,
"min": 3.9545454545454546,
"max": 24.886363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1095.0,
"min": 174.0,
"max": 1344.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.886363636363637,
"min": 3.9545454545454546,
"max": 24.886363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1095.0,
"min": 174.0,
"max": 1344.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1745611959",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1745612386"
},
"total": 427.6923993359999,
"count": 1,
"self": 0.38826743100003114,
"children": {
"run_training.setup": {
"total": 0.0226724199999353,
"count": 1,
"self": 0.0226724199999353
},
"TrainerController.start_learning": {
"total": 427.2814594849999,
"count": 1,
"self": 0.3581007440018311,
"children": {
"TrainerController._reset_env": {
"total": 3.5791910579998785,
"count": 1,
"self": 3.5791910579998785
},
"TrainerController.advance": {
"total": 423.2618842429981,
"count": 18192,
"self": 0.3809501569655822,
"children": {
"env_step": {
"total": 301.01459337401843,
"count": 18192,
"self": 230.42609100201776,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.37330827600977,
"count": 18192,
"self": 1.2935061140103699,
"children": {
"TorchPolicy.evaluate": {
"total": 69.0798021619994,
"count": 18192,
"self": 69.0798021619994
}
}
},
"workers": {
"total": 0.21519409599090977,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 425.65672407999773,
"count": 18192,
"is_parallel": true,
"self": 223.60286037200126,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005432940999980929,
"count": 1,
"is_parallel": true,
"self": 0.003886642999987089,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015462979999938398,
"count": 10,
"is_parallel": true,
"self": 0.0015462979999938398
}
}
},
"UnityEnvironment.step": {
"total": 0.061915031999888015,
"count": 1,
"is_parallel": true,
"self": 0.0006062759998712863,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004338399999141984,
"count": 1,
"is_parallel": true,
"self": 0.0004338399999141984
},
"communicator.exchange": {
"total": 0.058996549000085,
"count": 1,
"is_parallel": true,
"self": 0.058996549000085
},
"steps_from_proto": {
"total": 0.0018783670000175334,
"count": 1,
"is_parallel": true,
"self": 0.0004114069997740444,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001466960000243489,
"count": 10,
"is_parallel": true,
"self": 0.001466960000243489
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 202.05386370799647,
"count": 18191,
"is_parallel": true,
"self": 9.639769205979974,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.445570931997054,
"count": 18191,
"is_parallel": true,
"self": 5.445570931997054
},
"communicator.exchange": {
"total": 155.34447295600194,
"count": 18191,
"is_parallel": true,
"self": 155.34447295600194
},
"steps_from_proto": {
"total": 31.624050614017506,
"count": 18191,
"is_parallel": true,
"self": 5.715647537013865,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.90840307700364,
"count": 181910,
"is_parallel": true,
"self": 25.90840307700364
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.86634071201411,
"count": 18192,
"self": 0.4432816470259695,
"children": {
"process_trajectory": {
"total": 27.733540205988902,
"count": 18192,
"self": 27.32251714198901,
"children": {
"RLTrainer._checkpoint": {
"total": 0.41102306399989175,
"count": 4,
"self": 0.41102306399989175
}
}
},
"_update_policy": {
"total": 93.68951885899924,
"count": 90,
"self": 38.2016843310023,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.48783452799694,
"count": 4587,
"self": 55.48783452799694
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3100000160193304e-06,
"count": 1,
"self": 1.3100000160193304e-06
},
"TrainerController._save_models": {
"total": 0.0822821300000669,
"count": 1,
"self": 0.0007822560000931844,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08149987399997372,
"count": 1,
"self": 0.08149987399997372
}
}
}
}
}
}
}