ppo-Huggy / run_logs /timers.json
swritchie's picture
Huggy
067c615 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.401188611984253,
"min": 1.401188611984253,
"max": 1.4253637790679932,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71277.0625,
"min": 68626.9296875,
"max": 76268.765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 84.1107325383305,
"min": 78.60828025477707,
"max": 425.5762711864407,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49373.0,
"min": 49095.0,
"max": 50218.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999962.0,
"min": 49586.0,
"max": 1999962.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999962.0,
"min": 49586.0,
"max": 1999962.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.457559108734131,
"min": 0.0779602900147438,
"max": 2.493962526321411,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1442.587158203125,
"min": 9.121354103088379,
"max": 1514.3157958984375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7829421967826464,
"min": 1.772663309151291,
"max": 4.03501135528597,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2220.5870695114136,
"min": 207.40160717070103,
"max": 2434.4888726472855,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7829421967826464,
"min": 1.772663309151291,
"max": 4.03501135528597,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2220.5870695114136,
"min": 207.40160717070103,
"max": 2434.4888726472855,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01606295333476737,
"min": 0.013426645214591797,
"max": 0.019902821193358653,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.048188860004302114,
"min": 0.026853290429183593,
"max": 0.05970846358007596,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05547722660832934,
"min": 0.021943446062505246,
"max": 0.05799071888128916,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16643167982498802,
"min": 0.04511729429165522,
"max": 0.1686726164072752,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6537987820999923e-06,
"min": 3.6537987820999923e-06,
"max": 0.00029530357656547507,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0961396346299977e-05,
"min": 1.0961396346299977e-05,
"max": 0.0008438371687209499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121790000000001,
"min": 0.10121790000000001,
"max": 0.19843452499999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3036537,
"min": 0.20759330000000004,
"max": 0.5812790499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.07732099999999e-05,
"min": 7.07732099999999e-05,
"max": 0.004921882797499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002123196299999997,
"min": 0.0002123196299999997,
"max": 0.014065824595,
"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": "1767885429",
"python_version": "3.10.12 (main, Nov 4 2025, 08:48:33) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "1767888019"
},
"total": 2589.200208061,
"count": 1,
"self": 0.48451633300010144,
"children": {
"run_training.setup": {
"total": 0.02387736200000745,
"count": 1,
"self": 0.02387736200000745
},
"TrainerController.start_learning": {
"total": 2588.691814366,
"count": 1,
"self": 4.4876966200054085,
"children": {
"TrainerController._reset_env": {
"total": 3.593498772999965,
"count": 1,
"self": 3.593498772999965
},
"TrainerController.advance": {
"total": 2580.5130600229945,
"count": 232643,
"self": 4.576960114929989,
"children": {
"env_step": {
"total": 2096.2174037989907,
"count": 232643,
"self": 1690.9736076137783,
"children": {
"SubprocessEnvManager._take_step": {
"total": 402.4883482031005,
"count": 232643,
"self": 15.722891948133451,
"children": {
"TorchPolicy.evaluate": {
"total": 386.76545625496703,
"count": 223076,
"self": 386.76545625496703
}
}
},
"workers": {
"total": 2.7554479821119457,
"count": 232643,
"self": 0.0,
"children": {
"worker_root": {
"total": 2576.714043158003,
"count": 232643,
"is_parallel": true,
"self": 1202.3650690050135,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010865369999919494,
"count": 1,
"is_parallel": true,
"self": 0.0004041830000005575,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006823539999913919,
"count": 2,
"is_parallel": true,
"self": 0.0006823539999913919
}
}
},
"UnityEnvironment.step": {
"total": 0.055605964000051245,
"count": 1,
"is_parallel": true,
"self": 0.0003272980000019743,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020680299996911344,
"count": 1,
"is_parallel": true,
"self": 0.00020680299996911344
},
"communicator.exchange": {
"total": 0.05444230300008712,
"count": 1,
"is_parallel": true,
"self": 0.05444230300008712
},
"steps_from_proto": {
"total": 0.0006295599999930346,
"count": 1,
"is_parallel": true,
"self": 0.00015819000009287265,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00047136999990016193,
"count": 2,
"is_parallel": true,
"self": 0.00047136999990016193
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1374.3489741529893,
"count": 232642,
"is_parallel": true,
"self": 39.01230521286607,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.19941145608504,
"count": 232642,
"is_parallel": true,
"self": 85.19941145608504
},
"communicator.exchange": {
"total": 1158.0186649790678,
"count": 232642,
"is_parallel": true,
"self": 1158.0186649790678
},
"steps_from_proto": {
"total": 92.11859250497037,
"count": 232642,
"is_parallel": true,
"self": 32.3882526389192,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.73033986605117,
"count": 465284,
"is_parallel": true,
"self": 59.73033986605117
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 479.71869610907356,
"count": 232643,
"self": 6.6174466238837795,
"children": {
"process_trajectory": {
"total": 156.79950843019003,
"count": 232643,
"self": 155.6202072801907,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1793011499993327,
"count": 10,
"self": 1.1793011499993327
}
}
},
"_update_policy": {
"total": 316.30174105499975,
"count": 97,
"self": 251.19087222699568,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.11086882800407,
"count": 2910,
"self": 65.11086882800407
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.4600000011269e-07,
"count": 1,
"self": 9.4600000011269e-07
},
"TrainerController._save_models": {
"total": 0.09755800399989312,
"count": 1,
"self": 0.0012844139996559534,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09627359000023716,
"count": 1,
"self": 0.09627359000023716
}
}
}
}
}
}
}