ppo-Huggy / run_logs /timers.json
viiri2's picture
Huggy
c046efe verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4122334718704224,
"min": 1.4122334718704224,
"max": 1.4295217990875244,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72093.109375,
"min": 68503.1640625,
"max": 79342.5,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 75.78494623655914,
"min": 74.61724659606656,
"max": 409.2704918032787,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49336.0,
"min": 49212.0,
"max": 50110.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999943.0,
"min": 49608.0,
"max": 1999943.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999943.0,
"min": 49608.0,
"max": 1999943.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.463117837905884,
"min": 0.05510314553976059,
"max": 2.48136830329895,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1603.48974609375,
"min": 6.66748046875,
"max": 1603.48974609375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8473724809842906,
"min": 1.792290052106558,
"max": 3.988864319584913,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2504.6394851207733,
"min": 216.8670963048935,
"max": 2539.3390488624573,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8473724809842906,
"min": 1.792290052106558,
"max": 3.988864319584913,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2504.6394851207733,
"min": 216.8670963048935,
"max": 2539.3390488624573,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017644448909191448,
"min": 0.012764941072600778,
"max": 0.01998266000288519,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05293334672757434,
"min": 0.025529882145201556,
"max": 0.059541252248042534,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.058360934836996926,
"min": 0.021489225327968597,
"max": 0.05959214487423499,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17508280451099079,
"min": 0.042978450655937195,
"max": 0.17508280451099079,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.607698797466655e-06,
"min": 3.607698797466655e-06,
"max": 0.0002953636515454499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0823096392399965e-05,
"min": 1.0823096392399965e-05,
"max": 0.000844146018618,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120253333333333,
"min": 0.10120253333333333,
"max": 0.19845455,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3036076,
"min": 0.20753380000000005,
"max": 0.5813820000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.000641333333316e-05,
"min": 7.000641333333316e-05,
"max": 0.0049228820449999985,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021001923999999946,
"min": 0.00021001923999999946,
"max": 0.0140709618,
"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": "1751131404",
"python_version": "3.10.12 (main, Jun 28 2025, 19:55:49) [GCC 14.2.0]",
"command_line_arguments": "/home/durazell/torch/ml_agents_env/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1751132312"
},
"total": 907.455914915,
"count": 1,
"self": 0.16752443499899528,
"children": {
"run_training.setup": {
"total": 0.015361747000497417,
"count": 1,
"self": 0.015361747000497417
},
"TrainerController.start_learning": {
"total": 907.2730287330005,
"count": 1,
"self": 2.097754616347629,
"children": {
"TrainerController._reset_env": {
"total": 1.21616251299929,
"count": 1,
"self": 1.21616251299929
},
"TrainerController.advance": {
"total": 903.9038925096538,
"count": 232892,
"self": 1.9486423787411695,
"children": {
"env_step": {
"total": 649.0613738930497,
"count": 232892,
"self": 490.7924739290802,
"children": {
"SubprocessEnvManager._take_step": {
"total": 156.89146380206785,
"count": 232892,
"self": 6.544942190997972,
"children": {
"TorchPolicy.evaluate": {
"total": 150.34652161106987,
"count": 222973,
"self": 150.34652161106987
}
}
},
"workers": {
"total": 1.3774361619016418,
"count": 232892,
"self": 0.0,
"children": {
"worker_root": {
"total": 904.675406651917,
"count": 232892,
"is_parallel": true,
"self": 525.4423947060859,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00045777600007568253,
"count": 1,
"is_parallel": true,
"self": 0.0001132220004365081,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00034455399963917444,
"count": 2,
"is_parallel": true,
"self": 0.00034455399963917444
}
}
},
"UnityEnvironment.step": {
"total": 0.010386035000010452,
"count": 1,
"is_parallel": true,
"self": 0.00018022699896391714,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00012665700069192098,
"count": 1,
"is_parallel": true,
"self": 0.00012665700069192098
},
"communicator.exchange": {
"total": 0.009710342000289529,
"count": 1,
"is_parallel": true,
"self": 0.009710342000289529
},
"steps_from_proto": {
"total": 0.00036880900006508455,
"count": 1,
"is_parallel": true,
"self": 9.223200049746083e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0002765769995676237,
"count": 2,
"is_parallel": true,
"self": 0.0002765769995676237
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 379.2330119458311,
"count": 232891,
"is_parallel": true,
"self": 12.24067852157259,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.009858970815003,
"count": 232891,
"is_parallel": true,
"self": 21.009858970815003
},
"communicator.exchange": {
"total": 317.5386234536827,
"count": 232891,
"is_parallel": true,
"self": 317.5386234536827
},
"steps_from_proto": {
"total": 28.443850999760798,
"count": 232891,
"is_parallel": true,
"self": 9.75665854941144,
"children": {
"_process_rank_one_or_two_observation": {
"total": 18.687192450349357,
"count": 465782,
"is_parallel": true,
"self": 18.687192450349357
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 252.89387623786297,
"count": 232892,
"self": 3.0557421318399065,
"children": {
"process_trajectory": {
"total": 83.1321937650182,
"count": 232892,
"self": 82.5139509420178,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6182428230004007,
"count": 10,
"self": 0.6182428230004007
}
}
},
"_update_policy": {
"total": 166.70594034100486,
"count": 97,
"self": 142.21806299598757,
"children": {
"TorchPPOOptimizer.update": {
"total": 24.487877345017296,
"count": 2910,
"self": 24.487877345017296
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.709994290256873e-07,
"count": 1,
"self": 8.709994290256873e-07
},
"TrainerController._save_models": {
"total": 0.055218223000338185,
"count": 1,
"self": 0.0010453630002302816,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0541728600001079,
"count": 1,
"self": 0.0541728600001079
}
}
}
}
}
}
}