ppo-Huggy / run_logs /timers.json
Huggingfly's picture
Huggy for Deep RL Course
81d30f3
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4081884622573853,
"min": 1.4081884622573853,
"max": 1.4280356168746948,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68830.84375,
"min": 68830.84375,
"max": 76012.3046875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.37070524412296,
"min": 76.15100154083206,
"max": 382.8615384615385,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49422.0,
"min": 48772.0,
"max": 50085.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999957.0,
"min": 49922.0,
"max": 1999957.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999957.0,
"min": 49922.0,
"max": 1999957.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.418292284011841,
"min": -0.0029743919149041176,
"max": 2.4596128463745117,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1337.315673828125,
"min": -0.39559412002563477,
"max": 1569.2476806640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7515309333370133,
"min": 1.777528204864129,
"max": 3.935776709096275,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2074.5966061353683,
"min": 236.41125124692917,
"max": 2457.703495502472,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7515309333370133,
"min": 1.777528204864129,
"max": 3.935776709096275,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2074.5966061353683,
"min": 236.41125124692917,
"max": 2457.703495502472,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01674446332552988,
"min": 0.014203382957687912,
"max": 0.020161656502447535,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05023338997658963,
"min": 0.028406765915375824,
"max": 0.05804136816714163,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.056580123802026115,
"min": 0.022160486814876396,
"max": 0.06347084703544775,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16974037140607834,
"min": 0.04432097362975279,
"max": 0.18843155751625695,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.8248487250833335e-06,
"min": 3.8248487250833335e-06,
"max": 0.0002953512765495749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1474546175250001e-05,
"min": 1.1474546175250001e-05,
"max": 0.00084411346862885,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10127491666666666,
"min": 0.10127491666666666,
"max": 0.1984504250000001,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30382475,
"min": 0.20768505000000007,
"max": 0.5813711500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.361834166666666e-05,
"min": 7.361834166666666e-05,
"max": 0.0049226762075,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.000220855025,
"min": 0.000220855025,
"max": 0.014070420385,
"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": "1688325038",
"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": "1688327316"
},
"total": 2277.396683734,
"count": 1,
"self": 0.7942045419999886,
"children": {
"run_training.setup": {
"total": 0.04347170500000175,
"count": 1,
"self": 0.04347170500000175
},
"TrainerController.start_learning": {
"total": 2276.559007487,
"count": 1,
"self": 3.9981192649529476,
"children": {
"TrainerController._reset_env": {
"total": 4.300737624000021,
"count": 1,
"self": 4.300737624000021
},
"TrainerController.advance": {
"total": 2268.0874724590467,
"count": 232138,
"self": 4.25492749898649,
"children": {
"env_step": {
"total": 1776.34446665103,
"count": 232138,
"self": 1493.4016083958272,
"children": {
"SubprocessEnvManager._take_step": {
"total": 280.2484897081142,
"count": 232138,
"self": 16.46652201121333,
"children": {
"TorchPolicy.evaluate": {
"total": 263.7819676969009,
"count": 222872,
"self": 263.7819676969009
}
}
},
"workers": {
"total": 2.694368547088402,
"count": 232138,
"self": 0.0,
"children": {
"worker_root": {
"total": 2268.9231332980685,
"count": 232138,
"is_parallel": true,
"self": 1050.1995003270529,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009687740000572376,
"count": 1,
"is_parallel": true,
"self": 0.0002389900000707712,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007297839999864664,
"count": 2,
"is_parallel": true,
"self": 0.0007297839999864664
}
}
},
"UnityEnvironment.step": {
"total": 0.028791984000008597,
"count": 1,
"is_parallel": true,
"self": 0.00034282100000382343,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021270499996717263,
"count": 1,
"is_parallel": true,
"self": 0.00021270499996717263
},
"communicator.exchange": {
"total": 0.027502870000034818,
"count": 1,
"is_parallel": true,
"self": 0.027502870000034818
},
"steps_from_proto": {
"total": 0.0007335880000027828,
"count": 1,
"is_parallel": true,
"self": 0.0001956739999968704,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005379140000059124,
"count": 2,
"is_parallel": true,
"self": 0.0005379140000059124
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1218.7236329710156,
"count": 232137,
"is_parallel": true,
"self": 38.5405962319071,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.78072627607594,
"count": 232137,
"is_parallel": true,
"self": 76.78072627607594
},
"communicator.exchange": {
"total": 1010.8454295570541,
"count": 232137,
"is_parallel": true,
"self": 1010.8454295570541
},
"steps_from_proto": {
"total": 92.55688090597857,
"count": 232137,
"is_parallel": true,
"self": 32.68403881896154,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.872842087017034,
"count": 464274,
"is_parallel": true,
"self": 59.872842087017034
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 487.48807830903036,
"count": 232138,
"self": 5.8121051710865,
"children": {
"process_trajectory": {
"total": 127.16186801894344,
"count": 232138,
"self": 125.59850994294368,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5633580759997585,
"count": 10,
"self": 1.5633580759997585
}
}
},
"_update_policy": {
"total": 354.5141051190004,
"count": 97,
"self": 297.7617187209959,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.752386398004546,
"count": 2910,
"self": 56.752386398004546
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.244000031874748e-06,
"count": 1,
"self": 1.244000031874748e-06
},
"TrainerController._save_models": {
"total": 0.17267689500022243,
"count": 1,
"self": 0.002609835000384919,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1700670599998375,
"count": 1,
"self": 0.1700670599998375
}
}
}
}
}
}
}