rnd-Pyramids1 / run_logs /timers.json
amb007's picture
First Push
32b65de verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3038240671157837,
"min": 0.29767706990242004,
"max": 1.454626202583313,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 9163.333984375,
"min": 8925.548828125,
"max": 44127.5390625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989878.0,
"min": 29952.0,
"max": 989878.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989878.0,
"min": 29952.0,
"max": 989878.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5263857841491699,
"min": -0.12049926072359085,
"max": 0.5908653140068054,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 144.22970581054688,
"min": -29.16082191467285,
"max": 163.07882690429688,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.03339358791708946,
"min": 0.008526108227670193,
"max": 0.24725206196308136,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 9.149843215942383,
"min": 2.2167880535125732,
"max": 59.34049606323242,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07037054542029807,
"min": 0.06374284853746741,
"max": 0.07421795100575636,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.055558181304471,
"min": 0.4978445819915264,
"max": 1.055558181304471,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01596521967808941,
"min": 0.00012706576201843632,
"max": 0.016231415361796668,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23947829517134114,
"min": 0.0015247891442212358,
"max": 0.23947829517134114,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.485817504759999e-06,
"min": 7.485817504759999e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011228726257139998,
"min": 0.00011228726257139998,
"max": 0.0032246461251179996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249524,
"min": 0.10249524,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5374286,
"min": 1.3691136000000002,
"max": 2.5275213,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002592744759999999,
"min": 0.0002592744759999999,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003889117139999999,
"min": 0.003889117139999999,
"max": 0.10750071179999998,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012802531011402607,
"min": 0.01226204913109541,
"max": 0.45006701350212097,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.19203796982765198,
"min": 0.17166869342327118,
"max": 3.1504690647125244,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 335.7717391304348,
"min": 328.29347826086956,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30891.0,
"min": 15984.0,
"max": 33783.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.577241284367831,
"min": -1.0000000521540642,
"max": 1.6667441604442375,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 145.10619816184044,
"min": -32.000001668930054,
"max": 145.79519821703434,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.577241284367831,
"min": -1.0000000521540642,
"max": 1.6667441604442375,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 145.10619816184044,
"min": -32.000001668930054,
"max": 145.79519821703434,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.0442750143420594,
"min": 0.04166617828266918,
"max": 8.50676448829472,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.073301319469465,
"min": 3.799379298929125,
"max": 136.10823181271553,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1740842976",
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1740845194"
},
"total": 2218.3079400869997,
"count": 1,
"self": 0.47556848200019886,
"children": {
"run_training.setup": {
"total": 0.020215529999859427,
"count": 1,
"self": 0.020215529999859427
},
"TrainerController.start_learning": {
"total": 2217.8121560749996,
"count": 1,
"self": 1.3454211710213713,
"children": {
"TrainerController._reset_env": {
"total": 2.1244702549997783,
"count": 1,
"self": 2.1244702549997783
},
"TrainerController.advance": {
"total": 2214.2540654989775,
"count": 63898,
"self": 1.4239110100152175,
"children": {
"env_step": {
"total": 1535.9236686889649,
"count": 63898,
"self": 1381.5417153669873,
"children": {
"SubprocessEnvManager._take_step": {
"total": 153.58670614907396,
"count": 63898,
"self": 4.632785849201355,
"children": {
"TorchPolicy.evaluate": {
"total": 148.9539202998726,
"count": 62558,
"self": 148.9539202998726
}
}
},
"workers": {
"total": 0.7952471729036006,
"count": 63898,
"self": 0.0,
"children": {
"worker_root": {
"total": 2212.773033187873,
"count": 63898,
"is_parallel": true,
"self": 942.766344750808,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001987762000226212,
"count": 1,
"is_parallel": true,
"self": 0.0006638400000156253,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013239220002105867,
"count": 8,
"is_parallel": true,
"self": 0.0013239220002105867
}
}
},
"UnityEnvironment.step": {
"total": 0.049577341999793134,
"count": 1,
"is_parallel": true,
"self": 0.0005536069998015591,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004588310002873186,
"count": 1,
"is_parallel": true,
"self": 0.0004588310002873186
},
"communicator.exchange": {
"total": 0.046895281999695726,
"count": 1,
"is_parallel": true,
"self": 0.046895281999695726
},
"steps_from_proto": {
"total": 0.0016696220000085304,
"count": 1,
"is_parallel": true,
"self": 0.0003582030012694304,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013114189987391,
"count": 8,
"is_parallel": true,
"self": 0.0013114189987391
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1270.006688437065,
"count": 63897,
"is_parallel": true,
"self": 31.512054384782914,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.872140612016665,
"count": 63897,
"is_parallel": true,
"self": 22.872140612016665
},
"communicator.exchange": {
"total": 1119.7653907951953,
"count": 63897,
"is_parallel": true,
"self": 1119.7653907951953
},
"steps_from_proto": {
"total": 95.85710264506997,
"count": 63897,
"is_parallel": true,
"self": 19.42023325326727,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.4368693918027,
"count": 511176,
"is_parallel": true,
"self": 76.4368693918027
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 676.9064857999974,
"count": 63898,
"self": 2.720314851015246,
"children": {
"process_trajectory": {
"total": 127.50651627698244,
"count": 63898,
"self": 127.28013756398195,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22637871300048573,
"count": 2,
"self": 0.22637871300048573
}
}
},
"_update_policy": {
"total": 546.6796546719997,
"count": 444,
"self": 301.4707442209824,
"children": {
"TorchPPOOptimizer.update": {
"total": 245.20891045101735,
"count": 22803,
"self": 245.20891045101735
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.800005500437692e-07,
"count": 1,
"self": 9.800005500437692e-07
},
"TrainerController._save_models": {
"total": 0.0881981700003962,
"count": 1,
"self": 0.0015946550001899595,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08660351500020624,
"count": 1,
"self": 0.08660351500020624
}
}
}
}
}
}
}