ppo-Huggy / run_logs /timers.json
Aleksey Savin
Huggy RL first commit.
3503bb6
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4024523496627808,
"min": 1.4024523496627808,
"max": 1.4263604879379272,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69642.9765625,
"min": 68927.1484375,
"max": 77074.3828125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 98.02579365079364,
"min": 87.50088495575221,
"max": 413.1818181818182,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49405.0,
"min": 48926.0,
"max": 49995.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999895.0,
"min": 49656.0,
"max": 1999895.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999895.0,
"min": 49656.0,
"max": 1999895.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.406404495239258,
"min": 0.04645393788814545,
"max": 2.4757304191589355,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1212.827880859375,
"min": 5.574472427368164,
"max": 1369.761474609375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7505350497270387,
"min": 1.8717042981957397,
"max": 3.977399624445859,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1890.2696650624275,
"min": 224.60451578348875,
"max": 2171.3427405953407,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7505350497270387,
"min": 1.8717042981957397,
"max": 3.977399624445859,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1890.2696650624275,
"min": 224.60451578348875,
"max": 2171.3427405953407,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01464639171616808,
"min": 0.012825668693403713,
"max": 0.01958082007598326,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04393917514850424,
"min": 0.025651337386807426,
"max": 0.05705648353323341,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05101405075854726,
"min": 0.02152074705809355,
"max": 0.0638830812027057,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15304215227564177,
"min": 0.0430414941161871,
"max": 0.17330650513370832,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.53594882138333e-06,
"min": 3.53594882138333e-06,
"max": 0.00029536275154574997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.060784646414999e-05,
"min": 1.060784646414999e-05,
"max": 0.0008438367187210999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117861666666667,
"min": 0.10117861666666667,
"max": 0.19845424999999994,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30353585,
"min": 0.2074973000000001,
"max": 0.5812789,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.88129716666666e-05,
"min": 6.88129716666666e-05,
"max": 0.004922867075,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020643891499999982,
"min": 0.00020643891499999982,
"max": 0.014065817110000003,
"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": "1701172811",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701175185"
},
"total": 2374.367938077,
"count": 1,
"self": 0.4335680490003142,
"children": {
"run_training.setup": {
"total": 0.05680300099999158,
"count": 1,
"self": 0.05680300099999158
},
"TrainerController.start_learning": {
"total": 2373.8775670269997,
"count": 1,
"self": 4.359303946931959,
"children": {
"TrainerController._reset_env": {
"total": 3.4664222800000175,
"count": 1,
"self": 3.4664222800000175
},
"TrainerController.advance": {
"total": 2365.941085586068,
"count": 232271,
"self": 4.522185083924796,
"children": {
"env_step": {
"total": 1872.5424456830178,
"count": 232271,
"self": 1552.0006167110273,
"children": {
"SubprocessEnvManager._take_step": {
"total": 317.7725666859601,
"count": 232271,
"self": 16.269445422937565,
"children": {
"TorchPolicy.evaluate": {
"total": 301.50312126302254,
"count": 222982,
"self": 301.50312126302254
}
}
},
"workers": {
"total": 2.769262286030539,
"count": 232271,
"self": 0.0,
"children": {
"worker_root": {
"total": 2365.982801836062,
"count": 232271,
"is_parallel": true,
"self": 1104.4866166910763,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008048589999702926,
"count": 1,
"is_parallel": true,
"self": 0.00020912399997996545,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005957349999903272,
"count": 2,
"is_parallel": true,
"self": 0.0005957349999903272
}
}
},
"UnityEnvironment.step": {
"total": 0.06922976399999925,
"count": 1,
"is_parallel": true,
"self": 0.00031110500003705965,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022191799996562622,
"count": 1,
"is_parallel": true,
"self": 0.00022191799996562622
},
"communicator.exchange": {
"total": 0.0680322019999835,
"count": 1,
"is_parallel": true,
"self": 0.0680322019999835
},
"steps_from_proto": {
"total": 0.0006645390000130647,
"count": 1,
"is_parallel": true,
"self": 0.00018281999996361264,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000481719000049452,
"count": 2,
"is_parallel": true,
"self": 0.000481719000049452
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1261.496185144986,
"count": 232270,
"is_parallel": true,
"self": 40.021309907938985,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.35185471008202,
"count": 232270,
"is_parallel": true,
"self": 83.35185471008202
},
"communicator.exchange": {
"total": 1050.3227313950451,
"count": 232270,
"is_parallel": true,
"self": 1050.3227313950451
},
"steps_from_proto": {
"total": 87.80028913191961,
"count": 232270,
"is_parallel": true,
"self": 30.786898043838562,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.01339108808105,
"count": 464540,
"is_parallel": true,
"self": 57.01339108808105
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 488.87645481912506,
"count": 232271,
"self": 6.672201082050719,
"children": {
"process_trajectory": {
"total": 151.05269320007557,
"count": 232271,
"self": 149.90075788807593,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1519353119996367,
"count": 10,
"self": 1.1519353119996367
}
}
},
"_update_policy": {
"total": 331.1515605369988,
"count": 97,
"self": 268.69084124500074,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.46071929199803,
"count": 2910,
"self": 62.46071929199803
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0909998309216462e-06,
"count": 1,
"self": 1.0909998309216462e-06
},
"TrainerController._save_models": {
"total": 0.11075412299987875,
"count": 1,
"self": 0.0017672139997557679,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10898690900012298,
"count": 1,
"self": 0.10898690900012298
}
}
}
}
}
}
}