ppo-Huggy / run_logs /timers.json
DTambu's picture
Huggy
f614741 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4047949314117432,
"min": 1.4047949314117432,
"max": 1.4281859397888184,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70456.0859375,
"min": 69439.671875,
"max": 76029.453125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 77.86908517350157,
"min": 77.06793048973144,
"max": 406.8292682926829,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49369.0,
"min": 48784.0,
"max": 50040.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999973.0,
"min": 49531.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999973.0,
"min": 49531.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.458752393722534,
"min": 0.03899341821670532,
"max": 2.505568504333496,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1558.8489990234375,
"min": 4.75719690322876,
"max": 1561.1820068359375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.847037283310003,
"min": 1.6745507896679346,
"max": 4.056560039709485,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2439.0216376185417,
"min": 204.29519633948803,
"max": 2555.6328250169754,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.847037283310003,
"min": 1.6745507896679346,
"max": 4.056560039709485,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2439.0216376185417,
"min": 204.29519633948803,
"max": 2555.6328250169754,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.013723991309396095,
"min": 0.01293705539493304,
"max": 0.020577565147929515,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.041171973928188284,
"min": 0.027616803544030212,
"max": 0.055744222331365265,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05973815263973342,
"min": 0.0241241036914289,
"max": 0.0636533702413241,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17921445791920027,
"min": 0.0482482073828578,
"max": 0.18311385872463387,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.744448751883341e-06,
"min": 3.744448751883341e-06,
"max": 0.00029535772654742503,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1233346255650023e-05,
"min": 1.1233346255650023e-05,
"max": 0.0008440771686409499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10124811666666668,
"min": 0.10124811666666668,
"max": 0.19845257500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30374435000000005,
"min": 0.2076708,
"max": 0.5813590500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.22810216666668e-05,
"min": 7.22810216666668e-05,
"max": 0.004922783492500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002168430650000004,
"min": 0.0002168430650000004,
"max": 0.014069816595000003,
"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": "1744919093",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1744921638"
},
"total": 2545.1049766240003,
"count": 1,
"self": 0.5819187140000395,
"children": {
"run_training.setup": {
"total": 0.024093805000006796,
"count": 1,
"self": 0.024093805000006796
},
"TrainerController.start_learning": {
"total": 2544.498964105,
"count": 1,
"self": 4.514674573085813,
"children": {
"TrainerController._reset_env": {
"total": 3.0055633330000546,
"count": 1,
"self": 3.0055633330000546
},
"TrainerController.advance": {
"total": 2536.810193887915,
"count": 233120,
"self": 4.679485282899805,
"children": {
"env_step": {
"total": 2041.427313488021,
"count": 233120,
"self": 1601.1485443599777,
"children": {
"SubprocessEnvManager._take_step": {
"total": 437.5077495929472,
"count": 233120,
"self": 16.08991694407098,
"children": {
"TorchPolicy.evaluate": {
"total": 421.41783264887624,
"count": 222960,
"self": 421.41783264887624
}
}
},
"workers": {
"total": 2.771019535096002,
"count": 233120,
"self": 0.0,
"children": {
"worker_root": {
"total": 2536.941119656003,
"count": 233120,
"is_parallel": true,
"self": 1232.5215991869482,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011249949999410092,
"count": 1,
"is_parallel": true,
"self": 0.000300410999898304,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008245840000427052,
"count": 2,
"is_parallel": true,
"self": 0.0008245840000427052
}
}
},
"UnityEnvironment.step": {
"total": 0.031461956000043756,
"count": 1,
"is_parallel": true,
"self": 0.00033214799998404487,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022958699992159382,
"count": 1,
"is_parallel": true,
"self": 0.00022958699992159382
},
"communicator.exchange": {
"total": 0.03020637000008719,
"count": 1,
"is_parallel": true,
"self": 0.03020637000008719
},
"steps_from_proto": {
"total": 0.0006938510000509268,
"count": 1,
"is_parallel": true,
"self": 0.00021189599999615893,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004819550000547679,
"count": 2,
"is_parallel": true,
"self": 0.0004819550000547679
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1304.419520469055,
"count": 233119,
"is_parallel": true,
"self": 38.502600356979656,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.9798201799374,
"count": 233119,
"is_parallel": true,
"self": 85.9798201799374
},
"communicator.exchange": {
"total": 1089.3457357310213,
"count": 233119,
"is_parallel": true,
"self": 1089.3457357310213
},
"steps_from_proto": {
"total": 90.59136420111679,
"count": 233119,
"is_parallel": true,
"self": 33.54311764117506,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.04824655994173,
"count": 466238,
"is_parallel": true,
"self": 57.04824655994173
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 490.7033951169942,
"count": 233120,
"self": 6.639127885992252,
"children": {
"process_trajectory": {
"total": 178.50594875600223,
"count": 233120,
"self": 177.1599262220027,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3460225339995304,
"count": 10,
"self": 1.3460225339995304
}
}
},
"_update_policy": {
"total": 305.55831847499974,
"count": 97,
"self": 241.08147622500303,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.47684224999671,
"count": 2910,
"self": 64.47684224999671
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5599998732795939e-06,
"count": 1,
"self": 1.5599998732795939e-06
},
"TrainerController._save_models": {
"total": 0.16853075099970738,
"count": 1,
"self": 0.0023312919997806603,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16619945899992672,
"count": 1,
"self": 0.16619945899992672
}
}
}
}
}
}
}