ppo-Huggy / run_logs /timers.json
maldaer's picture
Huggy Trained
cfee8b5 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3974004983901978,
"min": 1.3974004983901978,
"max": 1.4235318899154663,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70764.359375,
"min": 68873.515625,
"max": 77543.2578125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.38102893890675,
"min": 74.14264264264264,
"max": 391.03125,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49375.0,
"min": 48662.0,
"max": 50052.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999966.0,
"min": 49908.0,
"max": 1999966.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999966.0,
"min": 49908.0,
"max": 1999966.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4785027503967285,
"min": 0.04072684422135353,
"max": 2.5100927352905273,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1541.628662109375,
"min": 5.172309398651123,
"max": 1641.524658203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.883577344022763,
"min": 1.843657582411616,
"max": 4.061768314037943,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2415.5851079821587,
"min": 234.14451296627522,
"max": 2560.7626383304596,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.883577344022763,
"min": 1.843657582411616,
"max": 4.061768314037943,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2415.5851079821587,
"min": 234.14451296627522,
"max": 2560.7626383304596,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017121282152301215,
"min": 0.0137090335561273,
"max": 0.02034568022677882,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.051363846456903645,
"min": 0.0274180671122546,
"max": 0.061037040680336455,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.059974379754728746,
"min": 0.023303677979856732,
"max": 0.06385701224207878,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17992313926418624,
"min": 0.046607355959713465,
"max": 0.18931159513692064,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.8087987304333316e-06,
"min": 3.8087987304333316e-06,
"max": 0.00029531242656252504,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1426396191299994e-05,
"min": 1.1426396191299994e-05,
"max": 0.0008442477185841001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10126956666666666,
"min": 0.10126956666666666,
"max": 0.198437475,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3038087,
"min": 0.20771525000000005,
"max": 0.5814159000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.335137666666664e-05,
"min": 7.335137666666664e-05,
"max": 0.004922030002499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022005412999999993,
"min": 0.00022005412999999993,
"max": 0.01407265341,
"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": "1712506953",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1712509487"
},
"total": 2534.236209541,
"count": 1,
"self": 0.43452108999963457,
"children": {
"run_training.setup": {
"total": 0.07388075899996238,
"count": 1,
"self": 0.07388075899996238
},
"TrainerController.start_learning": {
"total": 2533.727807692,
"count": 1,
"self": 4.525880578038596,
"children": {
"TrainerController._reset_env": {
"total": 3.1040002550000736,
"count": 1,
"self": 3.1040002550000736
},
"TrainerController.advance": {
"total": 2525.9801674549612,
"count": 233636,
"self": 4.823939600988069,
"children": {
"env_step": {
"total": 2043.407947673914,
"count": 233636,
"self": 1698.5410974679735,
"children": {
"SubprocessEnvManager._take_step": {
"total": 341.70743253298474,
"count": 233636,
"self": 18.226649122063577,
"children": {
"TorchPolicy.evaluate": {
"total": 323.48078341092116,
"count": 223038,
"self": 323.48078341092116
}
}
},
"workers": {
"total": 3.1594176729556693,
"count": 233636,
"self": 0.0,
"children": {
"worker_root": {
"total": 2526.196923310008,
"count": 233636,
"is_parallel": true,
"self": 1155.4671413490641,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008843199999546414,
"count": 1,
"is_parallel": true,
"self": 0.00022614299996348564,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006581769999911558,
"count": 2,
"is_parallel": true,
"self": 0.0006581769999911558
}
}
},
"UnityEnvironment.step": {
"total": 0.03115640499993333,
"count": 1,
"is_parallel": true,
"self": 0.00039719300002616365,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002258829999846057,
"count": 1,
"is_parallel": true,
"self": 0.0002258829999846057
},
"communicator.exchange": {
"total": 0.029735618000017894,
"count": 1,
"is_parallel": true,
"self": 0.029735618000017894
},
"steps_from_proto": {
"total": 0.0007977109999046661,
"count": 1,
"is_parallel": true,
"self": 0.00020351899991055689,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005941919999941092,
"count": 2,
"is_parallel": true,
"self": 0.0005941919999941092
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1370.729781960944,
"count": 233635,
"is_parallel": true,
"self": 40.94920998294674,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.11076725197802,
"count": 233635,
"is_parallel": true,
"self": 90.11076725197802
},
"communicator.exchange": {
"total": 1142.338087626049,
"count": 233635,
"is_parallel": true,
"self": 1142.338087626049
},
"steps_from_proto": {
"total": 97.3317170999702,
"count": 233635,
"is_parallel": true,
"self": 37.20620745898577,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.12550964098443,
"count": 467270,
"is_parallel": true,
"self": 60.12550964098443
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 477.74828018005917,
"count": 233636,
"self": 6.822019611130031,
"children": {
"process_trajectory": {
"total": 168.08819878892893,
"count": 233636,
"self": 166.70930627592952,
"children": {
"RLTrainer._checkpoint": {
"total": 1.378892512999414,
"count": 10,
"self": 1.378892512999414
}
}
},
"_update_policy": {
"total": 302.8380617800002,
"count": 97,
"self": 241.89269095100053,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.94537082899967,
"count": 2910,
"self": 60.94537082899967
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.03899992609513e-06,
"count": 1,
"self": 1.03899992609513e-06
},
"TrainerController._save_models": {
"total": 0.11775836500009973,
"count": 1,
"self": 0.0020482160002757155,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11571014899982401,
"count": 1,
"self": 0.11571014899982401
}
}
}
}
}
}
}