ppo-Huggy / run_logs /timers.json
pabloac31's picture
Huggy
690e792
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4063451290130615,
"min": 1.4063451290130615,
"max": 1.4269161224365234,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71414.203125,
"min": 68152.2578125,
"max": 77429.6171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 83.01013513513513,
"min": 77.39028213166144,
"max": 420.96638655462186,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49142.0,
"min": 48940.0,
"max": 50100.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999952.0,
"min": 49629.0,
"max": 1999952.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999952.0,
"min": 49629.0,
"max": 1999952.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.394263982772827,
"min": 0.06030566990375519,
"max": 2.5237252712249756,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1417.404296875,
"min": 7.1160688400268555,
"max": 1525.277587890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.730184687150491,
"min": 1.6827136144294577,
"max": 4.062346918955861,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2208.269334793091,
"min": 198.560206502676,
"max": 2402.8086639642715,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.730184687150491,
"min": 1.6827136144294577,
"max": 4.062346918955861,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2208.269334793091,
"min": 198.560206502676,
"max": 2402.8086639642715,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01677673245172223,
"min": 0.014598971183780425,
"max": 0.019887389594805426,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.050330197355166695,
"min": 0.030059751516091637,
"max": 0.05891181328333914,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06178315869636005,
"min": 0.022825241616616646,
"max": 0.06178315869636005,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18534947608908015,
"min": 0.04565048323323329,
"max": 0.18534947608908015,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.774698741799994e-06,
"min": 3.774698741799994e-06,
"max": 0.00029533125155625003,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1324096225399982e-05,
"min": 1.1324096225399982e-05,
"max": 0.00084405766864745,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1012582,
"min": 0.1012582,
"max": 0.19844375000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037746,
"min": 0.2076428,
"max": 0.5813525500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.278417999999992e-05,
"min": 7.278417999999992e-05,
"max": 0.004922343124999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021835253999999974,
"min": 0.00021835253999999974,
"max": 0.014069492245,
"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": "1673536281",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.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": "1673538496"
},
"total": 2215.9815400059997,
"count": 1,
"self": 0.44258687299952726,
"children": {
"run_training.setup": {
"total": 0.1047768600000154,
"count": 1,
"self": 0.1047768600000154
},
"TrainerController.start_learning": {
"total": 2215.434176273,
"count": 1,
"self": 4.039164986011201,
"children": {
"TrainerController._reset_env": {
"total": 7.367435679000096,
"count": 1,
"self": 7.367435679000096
},
"TrainerController.advance": {
"total": 2203.9134861339885,
"count": 232690,
"self": 4.012660841182424,
"children": {
"env_step": {
"total": 1736.6986280039062,
"count": 232690,
"self": 1462.9987132899585,
"children": {
"SubprocessEnvManager._take_step": {
"total": 271.0840055619377,
"count": 232690,
"self": 14.071818785963728,
"children": {
"TorchPolicy.evaluate": {
"total": 257.012186775974,
"count": 222982,
"self": 64.25594195594658,
"children": {
"TorchPolicy.sample_actions": {
"total": 192.7562448200274,
"count": 222982,
"self": 192.7562448200274
}
}
}
}
},
"workers": {
"total": 2.6159091520099764,
"count": 232690,
"self": 0.0,
"children": {
"worker_root": {
"total": 2206.0794242101265,
"count": 232690,
"is_parallel": true,
"self": 1004.6338221511128,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019036920000417012,
"count": 1,
"is_parallel": true,
"self": 0.0003042019999384138,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015994900001032875,
"count": 2,
"is_parallel": true,
"self": 0.0015994900001032875
}
}
},
"UnityEnvironment.step": {
"total": 0.026766142000042237,
"count": 1,
"is_parallel": true,
"self": 0.0002907820000928041,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001722859999517823,
"count": 1,
"is_parallel": true,
"self": 0.0001722859999517823
},
"communicator.exchange": {
"total": 0.025461231999997835,
"count": 1,
"is_parallel": true,
"self": 0.025461231999997835
},
"steps_from_proto": {
"total": 0.000841841999999815,
"count": 1,
"is_parallel": true,
"self": 0.00039196199998059456,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00044988000001922046,
"count": 2,
"is_parallel": true,
"self": 0.00044988000001922046
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1201.4456020590137,
"count": 232689,
"is_parallel": true,
"self": 34.841496528880725,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 74.71897269903491,
"count": 232689,
"is_parallel": true,
"self": 74.71897269903491
},
"communicator.exchange": {
"total": 995.5175114830341,
"count": 232689,
"is_parallel": true,
"self": 995.5175114830341
},
"steps_from_proto": {
"total": 96.36762134806384,
"count": 232689,
"is_parallel": true,
"self": 40.042091758948345,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.32552958911549,
"count": 465378,
"is_parallel": true,
"self": 56.32552958911549
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 463.2021972888999,
"count": 232690,
"self": 6.270256840788193,
"children": {
"process_trajectory": {
"total": 147.4652418731124,
"count": 232690,
"self": 146.30085884611208,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1643830270003264,
"count": 10,
"self": 1.1643830270003264
}
}
},
"_update_policy": {
"total": 309.4666985749993,
"count": 97,
"self": 256.08335057,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.383348004999334,
"count": 2910,
"self": 53.383348004999334
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.950002327561378e-07,
"count": 1,
"self": 7.950002327561378e-07
},
"TrainerController._save_models": {
"total": 0.11408867899990582,
"count": 1,
"self": 0.0022204619999683928,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11186821699993743,
"count": 1,
"self": 0.11186821699993743
}
}
}
}
}
}
}