ppo-HuggyPRO / run_logs /timers.json
Goodevile's picture
Huggy
f3650e5
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.2916309833526611,
"min": 1.2915687561035156,
"max": 1.4251359701156616,
"count": 200
},
"Huggy.Policy.Entropy.sum": {
"value": 62748.7265625,
"min": 59741.14453125,
"max": 76407.203125,
"count": 200
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 329.68,
"min": 82.06810631229236,
"max": 431.2758620689655,
"count": 200
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49452.0,
"min": 48779.0,
"max": 50433.0,
"count": 200
},
"Huggy.Step.mean": {
"value": 9999578.0,
"min": 49957.0,
"max": 9999578.0,
"count": 200
},
"Huggy.Step.sum": {
"value": 9999578.0,
"min": 49957.0,
"max": 9999578.0,
"count": 200
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 1.6703221797943115,
"min": 0.05299324542284012,
"max": 2.540935754776001,
"count": 200
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 250.54832458496094,
"min": 6.0942230224609375,
"max": 1451.6268310546875,
"count": 200
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 2.4956342581411204,
"min": 1.8659891737544019,
"max": 4.021854137746911,
"count": 200
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 374.34513872116804,
"min": 214.5887549817562,
"max": 2325.3284353017807,
"count": 200
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 2.4956342581411204,
"min": 1.8659891737544019,
"max": 4.021854137746911,
"count": 200
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 374.34513872116804,
"min": 214.5887549817562,
"max": 2325.3284353017807,
"count": 200
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014889436883256875,
"min": 0.012596011432469823,
"max": 0.021822114528913517,
"count": 200
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04466831064977062,
"min": 0.025192022864939646,
"max": 0.062307523610070345,
"count": 200
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.008070611997714472,
"min": 0.005934457539115101,
"max": 0.051857324937979385,
"count": 200
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.024211835993143416,
"min": 0.011868915078230203,
"max": 0.1505432691425085,
"count": 200
},
"Huggy.Policy.LearningRate.mean": {
"value": 8.272997242666613e-07,
"min": 8.272997242666613e-07,
"max": 0.00029906107531297503,
"count": 200
},
"Huggy.Policy.LearningRate.sum": {
"value": 2.481899172799984e-06,
"min": 2.481899172799984e-06,
"max": 0.0008887766437411196,
"count": 200
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1002757333333333,
"min": 0.1002757333333333,
"max": 0.19968702500000005,
"count": 200
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3008271999999999,
"min": 0.20158484999999995,
"max": 0.5962588800000002,
"count": 200
},
"Huggy.Policy.Beta.mean": {
"value": 2.3759093333333247e-05,
"min": 2.3759093333333247e-05,
"max": 0.0049843825475,
"count": 200
},
"Huggy.Policy.Beta.sum": {
"value": 7.127727999999974e-05,
"min": 7.127727999999974e-05,
"max": 0.014813318112000002,
"count": 200
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 200
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 200
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1688009857",
"python_version": "3.8.16 (default, Jun 12 2023, 18:09:05) \n[GCC 11.2.0]",
"command_line_arguments": "/home/goodevil/miniconda3/envs/pytorch/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy/Huggy --run-id=HuggyPRO --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1",
"numpy_version": "1.23.5",
"end_time_seconds": "1688018376"
},
"total": 8519.163834284001,
"count": 1,
"self": 0.2713567129976582,
"children": {
"run_training.setup": {
"total": 0.013944420003099367,
"count": 1,
"self": 0.013944420003099367
},
"TrainerController.start_learning": {
"total": 8518.878533151,
"count": 1,
"self": 11.654669693001779,
"children": {
"TrainerController._reset_env": {
"total": 2.330551264996757,
"count": 1,
"self": 2.330551264996757
},
"TrainerController.advance": {
"total": 8504.787484158995,
"count": 1151920,
"self": 11.634858913435892,
"children": {
"env_step": {
"total": 6874.867672177119,
"count": 1151920,
"self": 4229.102616494994,
"children": {
"SubprocessEnvManager._take_step": {
"total": 2637.8263518264866,
"count": 1151920,
"self": 41.023996407377126,
"children": {
"TorchPolicy.evaluate": {
"total": 2596.8023554191095,
"count": 1113565,
"self": 2596.8023554191095
}
}
},
"workers": {
"total": 7.938703855637868,
"count": 1151920,
"self": 0.0,
"children": {
"worker_root": {
"total": 8486.042124363346,
"count": 1151920,
"is_parallel": true,
"self": 4946.660866049606,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0006605009984923527,
"count": 1,
"is_parallel": true,
"self": 0.00012472699745558202,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005357740010367706,
"count": 2,
"is_parallel": true,
"self": 0.0005357740010367706
}
}
},
"UnityEnvironment.step": {
"total": 0.019192366999050137,
"count": 1,
"is_parallel": true,
"self": 0.00016084899107227102,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003551250047166832,
"count": 1,
"is_parallel": true,
"self": 0.0003551250047166832
},
"communicator.exchange": {
"total": 0.018295558002137113,
"count": 1,
"is_parallel": true,
"self": 0.018295558002137113
},
"steps_from_proto": {
"total": 0.0003808350011240691,
"count": 1,
"is_parallel": true,
"self": 0.00010619800013955683,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00027463700098451227,
"count": 2,
"is_parallel": true,
"self": 0.00027463700098451227
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 3539.3812583137405,
"count": 1151919,
"is_parallel": true,
"self": 69.59815967052418,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 120.98973706474499,
"count": 1151919,
"is_parallel": true,
"self": 120.98973706474499
},
"communicator.exchange": {
"total": 3198.4137097053317,
"count": 1151919,
"is_parallel": true,
"self": 3198.4137097053317
},
"steps_from_proto": {
"total": 150.37965187313966,
"count": 1151919,
"is_parallel": true,
"self": 56.965320362236525,
"children": {
"_process_rank_one_or_two_observation": {
"total": 93.41433151090314,
"count": 2303838,
"is_parallel": true,
"self": 93.41433151090314
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1618.2849530684398,
"count": 1151920,
"self": 18.37608996131894,
"children": {
"process_trajectory": {
"total": 592.6013195561318,
"count": 1151920,
"self": 586.3349458221055,
"children": {
"RLTrainer._checkpoint": {
"total": 6.266373734026274,
"count": 50,
"self": 6.266373734026274
}
}
},
"_update_policy": {
"total": 1007.3075435509891,
"count": 483,
"self": 617.190196560965,
"children": {
"TorchPPOOptimizer.update": {
"total": 390.1173469900241,
"count": 14490,
"self": 390.1173469900241
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.00004568696022e-07,
"count": 1,
"self": 6.00004568696022e-07
},
"TrainerController._save_models": {
"total": 0.10582743400300387,
"count": 1,
"self": 0.0015798490057932213,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10424758499721065,
"count": 1,
"self": 0.10424758499721065
}
}
}
}
}
}
}