jainamk's picture
First Push
aef26dc verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.965071439743042,
"min": 0.965071439743042,
"max": 2.867809772491455,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9214.501953125,
"min": 9214.501953125,
"max": 29369.240234375,
"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": 12.918429374694824,
"min": 0.3058375418186188,
"max": 12.918429374694824,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2519.09375,
"min": 59.33248519897461,
"max": 2621.71875,
"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.Losses.PolicyLoss.mean": {
"value": 0.06851300717886154,
"min": 0.06012037317222898,
"max": 0.07501047663690234,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27405202871544615,
"min": 0.2551748646095375,
"max": 0.36714971455954837,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19180287460924367,
"min": 0.11249032217721619,
"max": 0.29775367057790947,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7672114984369747,
"min": 0.44996128870886476,
"max": 1.4887683528895472,
"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.CumulativeReward.mean": {
"value": 25.045454545454547,
"min": 3.3181818181818183,
"max": 25.70909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1102.0,
"min": 146.0,
"max": 1414.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.045454545454547,
"min": 3.3181818181818183,
"max": 25.70909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1102.0,
"min": 146.0,
"max": 1414.0,
"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": "1711410764",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711411196"
},
"total": 431.6125465580001,
"count": 1,
"self": 0.4392847660000143,
"children": {
"run_training.setup": {
"total": 0.05471833700005391,
"count": 1,
"self": 0.05471833700005391
},
"TrainerController.start_learning": {
"total": 431.118543455,
"count": 1,
"self": 0.5271514340008707,
"children": {
"TrainerController._reset_env": {
"total": 2.7301270570000042,
"count": 1,
"self": 2.7301270570000042
},
"TrainerController.advance": {
"total": 427.7720401339992,
"count": 18199,
"self": 0.25179693802044767,
"children": {
"env_step": {
"total": 427.52024319597876,
"count": 18199,
"self": 274.9880422529769,
"children": {
"SubprocessEnvManager._take_step": {
"total": 152.27110768500359,
"count": 18199,
"self": 1.4071306330029074,
"children": {
"TorchPolicy.evaluate": {
"total": 150.86397705200068,
"count": 18199,
"self": 150.86397705200068
}
}
},
"workers": {
"total": 0.26109325799825456,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 430.03893946900473,
"count": 18199,
"is_parallel": true,
"self": 215.06205179800213,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007059993999973813,
"count": 1,
"is_parallel": true,
"self": 0.0055581620000566545,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001501831999917158,
"count": 10,
"is_parallel": true,
"self": 0.001501831999917158
}
}
},
"UnityEnvironment.step": {
"total": 0.036084652999988975,
"count": 1,
"is_parallel": true,
"self": 0.0007318119999126793,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037525000004734466,
"count": 1,
"is_parallel": true,
"self": 0.00037525000004734466
},
"communicator.exchange": {
"total": 0.03288117300007798,
"count": 1,
"is_parallel": true,
"self": 0.03288117300007798
},
"steps_from_proto": {
"total": 0.0020964179999509724,
"count": 1,
"is_parallel": true,
"self": 0.0005125309999129968,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015838870000379757,
"count": 10,
"is_parallel": true,
"self": 0.0015838870000379757
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 214.9768876710026,
"count": 18198,
"is_parallel": true,
"self": 9.946293392014923,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.202455665967705,
"count": 18198,
"is_parallel": true,
"self": 5.202455665967705
},
"communicator.exchange": {
"total": 167.33604364600944,
"count": 18198,
"is_parallel": true,
"self": 167.33604364600944
},
"steps_from_proto": {
"total": 32.49209496701053,
"count": 18198,
"is_parallel": true,
"self": 5.966385070052866,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.525709896957665,
"count": 181980,
"is_parallel": true,
"self": 26.525709896957665
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001442200000383309,
"count": 1,
"self": 0.0001442200000383309,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 422.35252906898097,
"count": 650763,
"is_parallel": true,
"self": 13.911634900835452,
"children": {
"process_trajectory": {
"total": 232.8563104101463,
"count": 650763,
"is_parallel": true,
"self": 232.13120213114632,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7251082789999828,
"count": 4,
"is_parallel": true,
"self": 0.7251082789999828
}
}
},
"_update_policy": {
"total": 175.5845837579992,
"count": 90,
"is_parallel": true,
"self": 49.69274313199173,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.89184062600748,
"count": 4587,
"is_parallel": true,
"self": 125.89184062600748
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08908060999988265,
"count": 1,
"self": 0.0009502129998963937,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08813039699998626,
"count": 1,
"self": 0.08813039699998626
}
}
}
}
}
}
}