ppo-Huggy / run_logs /timers.json
knoffel's picture
Huggy
9d075f2 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4131202697753906,
"min": 1.413079857826233,
"max": 1.423565149307251,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72084.6796875,
"min": 51755.68359375,
"max": 269279.84375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 105.78924731182796,
"min": 104.71789473684211,
"max": 376.8731343283582,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49192.0,
"min": 49025.0,
"max": 50501.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999890.0,
"min": 49931.0,
"max": 1999890.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999890.0,
"min": 49931.0,
"max": 1999890.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2955219745635986,
"min": 0.07826226204633713,
"max": 2.3292925357818604,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1076.599853515625,
"min": 18.156845092773438,
"max": 1098.015380859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7928782554069307,
"min": 1.5994393494108627,
"max": 3.9371629182725227,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1778.8599017858505,
"min": 258.9458881020546,
"max": 1797.3172799944878,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7928782554069307,
"min": 1.5994393494108627,
"max": 3.9371629182725227,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1778.8599017858505,
"min": 258.9458881020546,
"max": 1797.3172799944878,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016255841462407262,
"min": 0.01212340142519679,
"max": 0.019309578390998974,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04876752438722179,
"min": 0.02424680285039358,
"max": 0.05792873517299692,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0489630249225431,
"min": 0.014743209211155774,
"max": 0.0489630249225431,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1468890747676293,
"min": 0.029486418422311547,
"max": 0.1468890747676293,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.098098633999991e-06,
"min": 4.098098633999991e-06,
"max": 0.0002953878765373749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.2294295901999973e-05,
"min": 1.2294295901999973e-05,
"max": 0.0008439181686939499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.101366,
"min": 0.101366,
"max": 0.198462625,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.304098,
"min": 0.20796145,
"max": 0.58130605,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.816339999999981e-05,
"min": 7.816339999999981e-05,
"max": 0.0049232849875,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00023449019999999946,
"min": 0.00023449019999999946,
"max": 0.014067171895000001,
"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": "1736613618",
"python_version": "3.10.16 (main, Dec 4 2024, 08:53:38) [GCC 13.2.0]",
"command_line_arguments": "/home/hrichter/projects/hf_rl_course/.venv/bin/mlagents-learn /home/hrichter/projects/hf_rl_course/content/ml-agents/config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy-mp --no-graphics --num-envs=32 --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1736614352"
},
"total": 734.250364192998,
"count": 1,
"self": 0.5323062630013737,
"children": {
"run_training.setup": {
"total": 0.2869157899986021,
"count": 1,
"self": 0.2869157899986021
},
"TrainerController.start_learning": {
"total": 733.431142139998,
"count": 1,
"self": 0.5467636279936414,
"children": {
"TrainerController._reset_env": {
"total": 2.037717203002103,
"count": 1,
"self": 2.037717203002103
},
"TrainerController.advance": {
"total": 730.7628460230044,
"count": 7768,
"self": 0.15108564022739301,
"children": {
"env_step": {
"total": 416.6019123589358,
"count": 7768,
"self": 125.41878614153393,
"children": {
"SubprocessEnvManager._take_step": {
"total": 290.2305916363075,
"count": 234729,
"self": 9.837283263143036,
"children": {
"TorchPolicy.evaluate": {
"total": 280.3933083731645,
"count": 228845,
"self": 280.3933083731645
}
}
},
"workers": {
"total": 0.9525345810943691,
"count": 7768,
"self": 0.0,
"children": {
"worker_root": {
"total": 23465.509365453938,
"count": 234726,
"is_parallel": true,
"self": 22624.190179401645,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.022741498014511308,
"count": 32,
"is_parallel": true,
"self": 0.0055951490212464705,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.017146348993264837,
"count": 64,
"is_parallel": true,
"self": 0.017146348993264837
}
}
},
"UnityEnvironment.step": {
"total": 0.5873354549985379,
"count": 32,
"is_parallel": true,
"self": 0.006916628997714724,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0036634670104831457,
"count": 32,
"is_parallel": true,
"self": 0.0036634670104831457
},
"communicator.exchange": {
"total": 0.5584091749951767,
"count": 32,
"is_parallel": true,
"self": 0.5584091749951767
},
"steps_from_proto": {
"total": 0.0183461839951633,
"count": 32,
"is_parallel": true,
"self": 0.0049502399742777925,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.013395944020885509,
"count": 64,
"is_parallel": true,
"self": 0.013395944020885509
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 841.3191860522929,
"count": 234694,
"is_parallel": true,
"self": 26.958348805062997,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 48.180654894236795,
"count": 234694,
"is_parallel": true,
"self": 48.180654894236795
},
"communicator.exchange": {
"total": 706.8437248906266,
"count": 234694,
"is_parallel": true,
"self": 706.8437248906266
},
"steps_from_proto": {
"total": 59.336457462366525,
"count": 234694,
"is_parallel": true,
"self": 21.40152212467001,
"children": {
"_process_rank_one_or_two_observation": {
"total": 37.934935337696515,
"count": 469388,
"is_parallel": true,
"self": 37.934935337696515
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 314.0098480238412,
"count": 7768,
"self": 1.118876133728918,
"children": {
"process_trajectory": {
"total": 107.88227381509569,
"count": 7768,
"self": 107.009227194103,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8730466209926817,
"count": 10,
"self": 0.8730466209926817
}
}
},
"_update_policy": {
"total": 205.00869807501658,
"count": 96,
"self": 169.6087109192158,
"children": {
"TorchPPOOptimizer.update": {
"total": 35.39998715580077,
"count": 2880,
"self": 35.39998715580077
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.899987733457237e-07,
"count": 1,
"self": 8.899987733457237e-07
},
"TrainerController._save_models": {
"total": 0.08381439599907026,
"count": 1,
"self": 0.0035746590001508594,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0802397369989194,
"count": 1,
"self": 0.0802397369989194
}
}
}
}
}
}
}