ppo-Huggy / run_logs /timers.json
refrtzd's picture
Huggy
1226073 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4011844396591187,
"min": 1.4011844396591187,
"max": 1.4240236282348633,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71943.8125,
"min": 67835.1796875,
"max": 78299.9921875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 93.29080675422139,
"min": 79.90614886731392,
"max": 396.3333333333333,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49724.0,
"min": 49234.0,
"max": 50013.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999514.0,
"min": 49868.0,
"max": 1999514.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999514.0,
"min": 49868.0,
"max": 1999514.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4543650150299072,
"min": 0.021542629227042198,
"max": 2.481905698776245,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1308.176513671875,
"min": 2.69282865524292,
"max": 1503.62060546875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7999750598286597,
"min": 1.892035905957222,
"max": 3.9610639552922846,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2025.3867068886757,
"min": 236.50448824465275,
"max": 2379.71082341671,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7999750598286597,
"min": 1.892035905957222,
"max": 3.9610639552922846,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2025.3867068886757,
"min": 236.50448824465275,
"max": 2379.71082341671,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.013393612357483814,
"min": 0.012765280621048683,
"max": 0.01872792746144114,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.040180837072451445,
"min": 0.025530561242097367,
"max": 0.05400728858724809,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05321850081284841,
"min": 0.024106601905077695,
"max": 0.05928093983481328,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15965550243854523,
"min": 0.04821320381015539,
"max": 0.17374563155074915,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7021987659666636e-06,
"min": 3.7021987659666636e-06,
"max": 0.00029537445154184997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.110659629789999e-05,
"min": 1.110659629789999e-05,
"max": 0.00084435496854835,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10123403333333335,
"min": 0.10123403333333335,
"max": 0.19845815,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30370210000000003,
"min": 0.2076273,
"max": 0.58145165,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.15782633333333e-05,
"min": 7.15782633333333e-05,
"max": 0.004923061684999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002147347899999999,
"min": 0.0002147347899999999,
"max": 0.014074437335000004,
"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": "1760442478",
"python_version": "3.10.13 (main, Oct 14 2025, 13:44:10) [GCC 14.2.0]",
"command_line_arguments": "/home/chames/mlagents/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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1760445026"
},
"total": 2547.982311727,
"count": 1,
"self": 0.27308805899974686,
"children": {
"run_training.setup": {
"total": 0.016103513999951247,
"count": 1,
"self": 0.016103513999951247
},
"TrainerController.start_learning": {
"total": 2547.693120154,
"count": 1,
"self": 4.444579116000114,
"children": {
"TrainerController._reset_env": {
"total": 3.956066369999917,
"count": 1,
"self": 3.956066369999917
},
"TrainerController.advance": {
"total": 2539.1139799209996,
"count": 232660,
"self": 4.402641746031804,
"children": {
"env_step": {
"total": 2143.218688601967,
"count": 232660,
"self": 1411.0829045411313,
"children": {
"SubprocessEnvManager._take_step": {
"total": 729.0863458709277,
"count": 232660,
"self": 17.93274982693697,
"children": {
"TorchPolicy.evaluate": {
"total": 711.1535960439908,
"count": 223037,
"self": 711.1535960439908
}
}
},
"workers": {
"total": 3.0494381899081873,
"count": 232660,
"self": 0.0,
"children": {
"worker_root": {
"total": 2536.5269859170107,
"count": 232660,
"is_parallel": true,
"self": 1386.3917997049437,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0006672790000266104,
"count": 1,
"is_parallel": true,
"self": 0.00019433900001786242,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00047294000000874803,
"count": 2,
"is_parallel": true,
"self": 0.00047294000000874803
}
}
},
"UnityEnvironment.step": {
"total": 0.01325601500002449,
"count": 1,
"is_parallel": true,
"self": 0.0001427200002126483,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00010730700000749493,
"count": 1,
"is_parallel": true,
"self": 0.00010730700000749493
},
"communicator.exchange": {
"total": 0.01274635199979457,
"count": 1,
"is_parallel": true,
"self": 0.01274635199979457
},
"steps_from_proto": {
"total": 0.0002596360000097775,
"count": 1,
"is_parallel": true,
"self": 7.134600014069292e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00018828999986908457,
"count": 2,
"is_parallel": true,
"self": 0.00018828999986908457
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1150.135186212067,
"count": 232659,
"is_parallel": true,
"self": 25.026786517820938,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 34.5672695492392,
"count": 232659,
"is_parallel": true,
"self": 34.5672695492392
},
"communicator.exchange": {
"total": 1042.7061573800445,
"count": 232659,
"is_parallel": true,
"self": 1042.7061573800445
},
"steps_from_proto": {
"total": 47.83497276496246,
"count": 232659,
"is_parallel": true,
"self": 14.55446769091327,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.28050507404919,
"count": 465318,
"is_parallel": true,
"self": 33.28050507404919
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 391.49264957300034,
"count": 232660,
"self": 6.3800653750238325,
"children": {
"process_trajectory": {
"total": 152.01984219797532,
"count": 232660,
"self": 150.68522645297503,
"children": {
"RLTrainer._checkpoint": {
"total": 1.334615745000292,
"count": 10,
"self": 1.334615745000292
}
}
},
"_update_policy": {
"total": 233.09274200000118,
"count": 97,
"self": 162.59218343200746,
"children": {
"TorchPPOOptimizer.update": {
"total": 70.50055856799372,
"count": 2910,
"self": 70.50055856799372
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.54000359645579e-07,
"count": 1,
"self": 6.54000359645579e-07
},
"TrainerController._save_models": {
"total": 0.17849409300015395,
"count": 1,
"self": 0.0015439059998243465,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1769501870003296,
"count": 1,
"self": 0.1769501870003296
}
}
}
}
}
}
}