ppo-Huggy / run_logs /timers.json
gsgoncalves's picture
Huggy
48e4d0d verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4000345468521118,
"min": 1.4000345468521118,
"max": 1.4262560606002808,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70336.3359375,
"min": 68131.0234375,
"max": 78367.1015625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 74.1593984962406,
"min": 73.16172106824926,
"max": 408.0650406504065,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49316.0,
"min": 48830.0,
"max": 50192.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999972.0,
"min": 49565.0,
"max": 1999972.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999972.0,
"min": 49565.0,
"max": 1999972.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4986517429351807,
"min": 0.053738806396722794,
"max": 2.527451992034912,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1659.104736328125,
"min": 6.556134223937988,
"max": 1660.905517578125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8948793754161124,
"min": 1.6807575688743202,
"max": 4.033721280549661,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2586.1999052762985,
"min": 205.05242340266705,
"max": 2598.2109026908875,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8948793754161124,
"min": 1.6807575688743202,
"max": 4.033721280549661,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2586.1999052762985,
"min": 205.05242340266705,
"max": 2598.2109026908875,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01815687022689316,
"min": 0.013022185199467155,
"max": 0.01992060776174185,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05447061068067948,
"min": 0.02604437039893431,
"max": 0.05847847871967436,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04961551498207781,
"min": 0.01797105448010067,
"max": 0.05890657761030727,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14884654494623342,
"min": 0.03594210896020134,
"max": 0.17671973283092182,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.971248676283335e-06,
"min": 3.971248676283335e-06,
"max": 0.00029535285154905005,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1913746028850007e-05,
"min": 1.1913746028850007e-05,
"max": 0.00084409906863365,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10132371666666669,
"min": 0.10132371666666669,
"max": 0.19845094999999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3039711500000001,
"min": 0.20777585,
"max": 0.5813663499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.605346166666669e-05,
"min": 7.605346166666669e-05,
"max": 0.004922702404999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022816038500000007,
"min": 0.00022816038500000007,
"max": 0.014070180865,
"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": "1717680144",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1717682797"
},
"total": 2653.153485648,
"count": 1,
"self": 0.48611348599979465,
"children": {
"run_training.setup": {
"total": 0.08297693899999103,
"count": 1,
"self": 0.08297693899999103
},
"TrainerController.start_learning": {
"total": 2652.5843952230002,
"count": 1,
"self": 4.746880081870131,
"children": {
"TrainerController._reset_env": {
"total": 3.5925073829999974,
"count": 1,
"self": 3.5925073829999974
},
"TrainerController.advance": {
"total": 2644.0737763871302,
"count": 233287,
"self": 5.046366604991363,
"children": {
"env_step": {
"total": 2029.8753116610756,
"count": 233287,
"self": 1668.7839439831082,
"children": {
"SubprocessEnvManager._take_step": {
"total": 357.9888733239003,
"count": 233287,
"self": 16.885994375020005,
"children": {
"TorchPolicy.evaluate": {
"total": 341.1028789488803,
"count": 222970,
"self": 341.1028789488803
}
}
},
"workers": {
"total": 3.1024943540671757,
"count": 233287,
"self": 0.0,
"children": {
"worker_root": {
"total": 2645.060538164948,
"count": 233287,
"is_parallel": true,
"self": 1298.606455039001,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001059347000023081,
"count": 1,
"is_parallel": true,
"self": 0.00028217399994900916,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007771730000740718,
"count": 2,
"is_parallel": true,
"self": 0.0007771730000740718
}
}
},
"UnityEnvironment.step": {
"total": 0.03013040199994066,
"count": 1,
"is_parallel": true,
"self": 0.00039683100010279304,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022203699995770876,
"count": 1,
"is_parallel": true,
"self": 0.00022203699995770876
},
"communicator.exchange": {
"total": 0.028753164999898218,
"count": 1,
"is_parallel": true,
"self": 0.028753164999898218
},
"steps_from_proto": {
"total": 0.0007583689999819399,
"count": 1,
"is_parallel": true,
"self": 0.00020711100000880833,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005512579999731315,
"count": 2,
"is_parallel": true,
"self": 0.0005512579999731315
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1346.454083125947,
"count": 233286,
"is_parallel": true,
"self": 41.49502316091889,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.60076637402813,
"count": 233286,
"is_parallel": true,
"self": 85.60076637402813
},
"communicator.exchange": {
"total": 1122.2313314419541,
"count": 233286,
"is_parallel": true,
"self": 1122.2313314419541
},
"steps_from_proto": {
"total": 97.12696214904577,
"count": 233286,
"is_parallel": true,
"self": 34.955084907997616,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.17187724104815,
"count": 466572,
"is_parallel": true,
"self": 62.17187724104815
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 609.1520981210634,
"count": 233287,
"self": 7.036333154038971,
"children": {
"process_trajectory": {
"total": 168.23364567902138,
"count": 233287,
"self": 166.44582698602107,
"children": {
"RLTrainer._checkpoint": {
"total": 1.787818693000304,
"count": 10,
"self": 1.787818693000304
}
}
},
"_update_policy": {
"total": 433.8821192880031,
"count": 97,
"self": 352.7368423639921,
"children": {
"TorchPPOOptimizer.update": {
"total": 81.145276924011,
"count": 2910,
"self": 81.145276924011
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0680000741558615e-06,
"count": 1,
"self": 1.0680000741558615e-06
},
"TrainerController._save_models": {
"total": 0.17123030299990205,
"count": 1,
"self": 0.002657715000168537,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16857258799973351,
"count": 1,
"self": 0.16857258799973351
}
}
}
}
}
}
}