ppo-Huggy / run_logs /timers.json
Sandf1sh's picture
Huggy
72d5a55 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4042348861694336,
"min": 1.4042348861694336,
"max": 1.4305825233459473,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71458.703125,
"min": 66288.6484375,
"max": 78181.7890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 120.89756097560975,
"min": 103.28364389233954,
"max": 364.91970802919707,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49568.0,
"min": 48881.0,
"max": 50346.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999980.0,
"min": 49856.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999980.0,
"min": 49856.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2719836235046387,
"min": 0.1288813352584839,
"max": 2.3445117473602295,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 931.5133056640625,
"min": 17.527862548828125,
"max": 1094.886962890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5031963345481127,
"min": 1.7931748505900889,
"max": 3.722019445079297,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1436.3104971647263,
"min": 243.87177968025208,
"max": 1738.1830808520317,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5031963345481127,
"min": 1.7931748505900889,
"max": 3.722019445079297,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1436.3104971647263,
"min": 243.87177968025208,
"max": 1738.1830808520317,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01627317501915968,
"min": 0.012830750417591238,
"max": 0.021092787159917255,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03254635003831936,
"min": 0.025661500835182476,
"max": 0.0563199188055781,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04793315151085456,
"min": 0.021237022181351976,
"max": 0.06232206494443946,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09586630302170912,
"min": 0.04247404436270395,
"max": 0.1869661948333184,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.423973525375006e-06,
"min": 4.423973525375006e-06,
"max": 0.000295317526560825,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.847947050750012e-06,
"min": 8.847947050750012e-06,
"max": 0.0008440291686569498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10147462500000001,
"min": 0.10147462500000001,
"max": 0.19843917499999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20294925000000003,
"min": 0.20294925000000003,
"max": 0.5813430500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.358378750000011e-05,
"min": 8.358378750000011e-05,
"max": 0.0049221148325,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016716757500000022,
"min": 0.00016716757500000022,
"max": 0.014069018195000001,
"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": "1750684997",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1750687384"
},
"total": 2387.583620493,
"count": 1,
"self": 0.3934870780003621,
"children": {
"run_training.setup": {
"total": 0.03465491299994028,
"count": 1,
"self": 0.03465491299994028
},
"TrainerController.start_learning": {
"total": 2387.155478502,
"count": 1,
"self": 4.294256101982228,
"children": {
"TrainerController._reset_env": {
"total": 3.201435884000034,
"count": 1,
"self": 3.201435884000034
},
"TrainerController.advance": {
"total": 2379.5586585020174,
"count": 230658,
"self": 4.313531188135585,
"children": {
"env_step": {
"total": 1914.4376776809438,
"count": 230658,
"self": 1516.1167107980546,
"children": {
"SubprocessEnvManager._take_step": {
"total": 395.7286759529951,
"count": 230658,
"self": 15.249134723978386,
"children": {
"TorchPolicy.evaluate": {
"total": 380.4795412290167,
"count": 222956,
"self": 380.4795412290167
}
}
},
"workers": {
"total": 2.5922909298942614,
"count": 230658,
"self": 0.0,
"children": {
"worker_root": {
"total": 2379.91900854299,
"count": 230658,
"is_parallel": true,
"self": 1140.4503146429586,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008589550000124291,
"count": 1,
"is_parallel": true,
"self": 0.000248633000069276,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006103219999431531,
"count": 2,
"is_parallel": true,
"self": 0.0006103219999431531
}
}
},
"UnityEnvironment.step": {
"total": 0.028989010000032067,
"count": 1,
"is_parallel": true,
"self": 0.0003275459999940722,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003139430000373977,
"count": 1,
"is_parallel": true,
"self": 0.0003139430000373977
},
"communicator.exchange": {
"total": 0.02769320400000197,
"count": 1,
"is_parallel": true,
"self": 0.02769320400000197
},
"steps_from_proto": {
"total": 0.0006543169999986276,
"count": 1,
"is_parallel": true,
"self": 0.00017722300003697455,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000477093999961653,
"count": 2,
"is_parallel": true,
"self": 0.000477093999961653
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1239.4686939000314,
"count": 230657,
"is_parallel": true,
"self": 36.772347162002916,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.28032356701317,
"count": 230657,
"is_parallel": true,
"self": 80.28032356701317
},
"communicator.exchange": {
"total": 1034.6875975409737,
"count": 230657,
"is_parallel": true,
"self": 1034.6875975409737
},
"steps_from_proto": {
"total": 87.72842563004156,
"count": 230657,
"is_parallel": true,
"self": 32.51144347209424,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.216982157947314,
"count": 461314,
"is_parallel": true,
"self": 55.216982157947314
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 460.8074496329381,
"count": 230658,
"self": 6.5873969538752135,
"children": {
"process_trajectory": {
"total": 142.26724625206157,
"count": 230658,
"self": 140.9304954710625,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3367507809990684,
"count": 10,
"self": 1.3367507809990684
}
}
},
"_update_policy": {
"total": 311.9528064270013,
"count": 96,
"self": 249.7445675460002,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.20823888100108,
"count": 2880,
"self": 62.20823888100108
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.619999789516442e-07,
"count": 1,
"self": 8.619999789516442e-07
},
"TrainerController._save_models": {
"total": 0.10112715200011735,
"count": 1,
"self": 0.0018297569999958796,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09929739500012147,
"count": 1,
"self": 0.09929739500012147
}
}
}
}
}
}
}