ppo-Huggy / run_logs /timers.json
YaoLiu61's picture
Huggy
8ba5809 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4032292366027832,
"min": 1.4032292366027832,
"max": 1.4271976947784424,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71542.2421875,
"min": 68401.640625,
"max": 77572.59375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 101.36713995943205,
"min": 84.81958762886597,
"max": 390.6511627906977,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49974.0,
"min": 48911.0,
"max": 50394.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999926.0,
"min": 49884.0,
"max": 1999926.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999926.0,
"min": 49884.0,
"max": 1999926.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3687241077423096,
"min": 0.3175739645957947,
"max": 2.426858425140381,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1167.781005859375,
"min": 40.64946746826172,
"max": 1382.8958740234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.671154824521914,
"min": 1.9318595093209296,
"max": 3.9177938974740214,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1809.8793284893036,
"min": 247.278017193079,
"max": 2233.142521560192,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.671154824521914,
"min": 1.9318595093209296,
"max": 3.9177938974740214,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1809.8793284893036,
"min": 247.278017193079,
"max": 2233.142521560192,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016414107914978455,
"min": 0.014009926464253416,
"max": 0.021439326555506948,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04924232374493537,
"min": 0.028019852928506832,
"max": 0.05994057842569116,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04745914741522736,
"min": 0.0201817030294074,
"max": 0.05545707046985626,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14237744224568208,
"min": 0.04159715510904789,
"max": 0.15850698451201123,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.234298921933343e-06,
"min": 3.234298921933343e-06,
"max": 0.00029533575155474994,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.702896765800028e-06,
"min": 9.702896765800028e-06,
"max": 0.0008440830186389999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10107806666666667,
"min": 0.10107806666666667,
"max": 0.19844525000000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3032342,
"min": 0.20729880000000006,
"max": 0.5813609999999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.379552666666683e-05,
"min": 6.379552666666683e-05,
"max": 0.004922417975000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001913865800000005,
"min": 0.0001913865800000005,
"max": 0.014069913899999998,
"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": "1730299388",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./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": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1730301843"
},
"total": 2454.954956872,
"count": 1,
"self": 0.5794520519998514,
"children": {
"run_training.setup": {
"total": 0.060604090999959226,
"count": 1,
"self": 0.060604090999959226
},
"TrainerController.start_learning": {
"total": 2454.3149007290003,
"count": 1,
"self": 4.665529639044053,
"children": {
"TrainerController._reset_env": {
"total": 5.50743892100013,
"count": 1,
"self": 5.50743892100013
},
"TrainerController.advance": {
"total": 2443.9572713649563,
"count": 231957,
"self": 4.436884206908417,
"children": {
"env_step": {
"total": 1927.755696576962,
"count": 231957,
"self": 1513.1113955648568,
"children": {
"SubprocessEnvManager._take_step": {
"total": 411.8870632139535,
"count": 231957,
"self": 15.875079927907109,
"children": {
"TorchPolicy.evaluate": {
"total": 396.0119832860464,
"count": 223067,
"self": 396.0119832860464
}
}
},
"workers": {
"total": 2.757237798151664,
"count": 231957,
"self": 0.0,
"children": {
"worker_root": {
"total": 2446.989781780999,
"count": 231957,
"is_parallel": true,
"self": 1216.1401550409362,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009505660000286298,
"count": 1,
"is_parallel": true,
"self": 0.00027299799990032625,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006775680001283035,
"count": 2,
"is_parallel": true,
"self": 0.0006775680001283035
}
}
},
"UnityEnvironment.step": {
"total": 0.030949194999948304,
"count": 1,
"is_parallel": true,
"self": 0.0005063459998382314,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002521460000934894,
"count": 1,
"is_parallel": true,
"self": 0.0002521460000934894
},
"communicator.exchange": {
"total": 0.02942224100002022,
"count": 1,
"is_parallel": true,
"self": 0.02942224100002022
},
"steps_from_proto": {
"total": 0.0007684619999963616,
"count": 1,
"is_parallel": true,
"self": 0.000192088999938278,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005763730000580836,
"count": 2,
"is_parallel": true,
"self": 0.0005763730000580836
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1230.8496267400626,
"count": 231956,
"is_parallel": true,
"self": 37.80824415510165,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.09543143592941,
"count": 231956,
"is_parallel": true,
"self": 81.09543143592941
},
"communicator.exchange": {
"total": 1023.7072809129243,
"count": 231956,
"is_parallel": true,
"self": 1023.7072809129243
},
"steps_from_proto": {
"total": 88.23867023610728,
"count": 231956,
"is_parallel": true,
"self": 31.374911822168542,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.86375841393874,
"count": 463912,
"is_parallel": true,
"self": 56.86375841393874
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 511.7646905810859,
"count": 231957,
"self": 6.622950017054109,
"children": {
"process_trajectory": {
"total": 161.05640591003248,
"count": 231957,
"self": 159.5169622580322,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5394436520002728,
"count": 10,
"self": 1.5394436520002728
}
}
},
"_update_policy": {
"total": 344.0853346539993,
"count": 97,
"self": 276.213571199994,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.8717634540053,
"count": 2910,
"self": 67.8717634540053
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4450001799559686e-06,
"count": 1,
"self": 1.4450001799559686e-06
},
"TrainerController._save_models": {
"total": 0.18465935899985197,
"count": 1,
"self": 0.0030815359996267944,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18157782300022518,
"count": 1,
"self": 0.18157782300022518
}
}
}
}
}
}
}