ppo-Huggy / run_logs /timers.json
songhat's picture
Huggy
bc3c31a verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4024018049240112,
"min": 1.4024018049240112,
"max": 1.4240174293518066,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70180.390625,
"min": 69075.921875,
"max": 76752.6171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.65066225165563,
"min": 73.75336322869956,
"max": 423.8305084745763,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49317.0,
"min": 48772.0,
"max": 50109.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999939.0,
"min": 49827.0,
"max": 1999939.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999939.0,
"min": 49827.0,
"max": 1999939.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.430752992630005,
"min": 0.09272418171167374,
"max": 2.510103940963745,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1468.1748046875,
"min": 10.848729133605957,
"max": 1628.1544189453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7723982685449107,
"min": 1.7477544255745716,
"max": 4.060642631380421,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2278.528554201126,
"min": 204.48726779222488,
"max": 2575.5047209858894,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7723982685449107,
"min": 1.7477544255745716,
"max": 4.060642631380421,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2278.528554201126,
"min": 204.48726779222488,
"max": 2575.5047209858894,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01384590308751083,
"min": 0.01229595957265701,
"max": 0.02107925393502228,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04153770926253249,
"min": 0.02459191914531402,
"max": 0.05895777370994135,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05570911007622878,
"min": 0.020852677058428526,
"max": 0.06129512070781654,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16712733022868634,
"min": 0.04170535411685705,
"max": 0.18388536212344964,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7556487481499967e-06,
"min": 3.7556487481499967e-06,
"max": 0.000295309876563375,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.126694624444999e-05,
"min": 1.126694624444999e-05,
"max": 0.0008441698686100499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10125184999999998,
"min": 0.10125184999999998,
"max": 0.19843662500000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30375554999999993,
"min": 0.20767385,
"max": 0.5813899500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.246731499999994e-05,
"min": 7.246731499999994e-05,
"max": 0.004921987587500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021740194499999982,
"min": 0.00021740194499999982,
"max": 0.014071358505000003,
"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": "1751353463",
"python_version": "3.10.18 (main, Jun 5 2025, 13:14:17) [GCC 11.2.0]",
"command_line_arguments": "/home/rhs/miniconda3/envs/RL/bin/mlagents-learn ml-agents/config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1751356000"
},
"total": 2536.897799221042,
"count": 1,
"self": 0.3197552080382593,
"children": {
"run_training.setup": {
"total": 0.016965968010481447,
"count": 1,
"self": 0.016965968010481447
},
"TrainerController.start_learning": {
"total": 2536.5610780449933,
"count": 1,
"self": 2.623909568937961,
"children": {
"TrainerController._reset_env": {
"total": 2.1358918859623373,
"count": 1,
"self": 2.1358918859623373
},
"TrainerController.advance": {
"total": 2531.7335757050896,
"count": 233194,
"self": 2.408196337695699,
"children": {
"env_step": {
"total": 2218.571237474738,
"count": 233194,
"self": 1985.9242483074777,
"children": {
"SubprocessEnvManager._take_step": {
"total": 230.96985651395516,
"count": 233194,
"self": 9.47508355928585,
"children": {
"TorchPolicy.evaluate": {
"total": 221.49477295466932,
"count": 222950,
"self": 221.49477295466932
}
}
},
"workers": {
"total": 1.677132653305307,
"count": 233194,
"self": 0.0,
"children": {
"worker_root": {
"total": 2526.2732386296266,
"count": 233194,
"is_parallel": true,
"self": 776.5605829414562,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018957550055347383,
"count": 1,
"is_parallel": true,
"self": 0.0007553559844382107,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011403990210965276,
"count": 2,
"is_parallel": true,
"self": 0.0011403990210965276
}
}
},
"UnityEnvironment.step": {
"total": 0.040787309990264475,
"count": 1,
"is_parallel": true,
"self": 0.00044635700760409236,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003356279921717942,
"count": 1,
"is_parallel": true,
"self": 0.0003356279921717942
},
"communicator.exchange": {
"total": 0.03895021800417453,
"count": 1,
"is_parallel": true,
"self": 0.03895021800417453
},
"steps_from_proto": {
"total": 0.0010551069863140583,
"count": 1,
"is_parallel": true,
"self": 0.00032102601835504174,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007340809679590166,
"count": 2,
"is_parallel": true,
"self": 0.0007340809679590166
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1749.7126556881703,
"count": 233193,
"is_parallel": true,
"self": 57.276696043729316,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 127.33223997731693,
"count": 233193,
"is_parallel": true,
"self": 127.33223997731693
},
"communicator.exchange": {
"total": 1432.4101672300603,
"count": 233193,
"is_parallel": true,
"self": 1432.4101672300603
},
"steps_from_proto": {
"total": 132.69355243706377,
"count": 233193,
"is_parallel": true,
"self": 47.98886157461675,
"children": {
"_process_rank_one_or_two_observation": {
"total": 84.70469086244702,
"count": 466386,
"is_parallel": true,
"self": 84.70469086244702
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 310.75414189265575,
"count": 233194,
"self": 3.3387639995780773,
"children": {
"process_trajectory": {
"total": 96.5010124440305,
"count": 233194,
"self": 95.6263415029971,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8746709410334006,
"count": 10,
"self": 0.8746709410334006
}
}
},
"_update_policy": {
"total": 210.91436544904718,
"count": 97,
"self": 156.19926170789404,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.71510374115314,
"count": 2910,
"self": 54.71510374115314
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.850467227399349e-07,
"count": 1,
"self": 7.850467227399349e-07
},
"TrainerController._save_models": {
"total": 0.06770009995670989,
"count": 1,
"self": 0.0010682579595595598,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06663184199715033,
"count": 1,
"self": 0.06663184199715033
}
}
}
}
}
}
}