Dione25's picture
First Push
2a0b4ee verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.123753309249878,
"min": 1.123753309249878,
"max": 2.8441882133483887,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 56070.79296875,
"min": 56070.79296875,
"max": 143665.640625,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 49936.0,
"max": 499976.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 49936.0,
"max": 499976.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.786314964294434,
"min": 0.5156550407409668,
"max": 12.786314964294434,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 12824.673828125,
"min": 511.52978515625,
"max": 12824.673828125,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 50347.0,
"min": 48158.0,
"max": 50347.0,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.897233201581027,
"min": 5.400826446280992,
"max": 25.976284584980238,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 6552.0,
"min": 1307.0,
"max": 6572.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.897233201581027,
"min": 5.400826446280992,
"max": 25.976284584980238,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 6552.0,
"min": 1307.0,
"max": 6572.0,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06950577638740457,
"min": 0.06697199987758085,
"max": 0.07267147787004424,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2780231055496183,
"min": 0.2678879995103234,
"max": 0.35860399117330855,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1932177474557915,
"min": 0.16070794140390465,
"max": 0.2696034466409508,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.772870989823166,
"min": 0.6428317656156186,
"max": 1.348017233204754,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.4576495141200002e-05,
"min": 1.4576495141200002e-05,
"max": 0.0002841864052712,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.830598056480001e-05,
"min": 5.830598056480001e-05,
"max": 0.0012797184734272,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1048588,
"min": 0.1048588,
"max": 0.1947288,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4194352,
"min": 0.4194352,
"max": 0.9265728,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00025245411999999995,
"min": 0.00025245411999999995,
"max": 0.00473696712,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0010098164799999998,
"min": 0.0010098164799999998,
"max": 0.02133598272,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1749855163",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1749856188"
},
"total": 1025.1004679060002,
"count": 1,
"self": 0.4350641070002439,
"children": {
"run_training.setup": {
"total": 0.022252680999827135,
"count": 1,
"self": 0.022252680999827135
},
"TrainerController.start_learning": {
"total": 1024.643151118,
"count": 1,
"self": 0.8149308649790328,
"children": {
"TrainerController._reset_env": {
"total": 3.418899008999915,
"count": 1,
"self": 3.418899008999915
},
"TrainerController.advance": {
"total": 1020.3316534990213,
"count": 45464,
"self": 0.8996741749688226,
"children": {
"env_step": {
"total": 729.1197099640756,
"count": 45464,
"self": 559.2884981370812,
"children": {
"SubprocessEnvManager._take_step": {
"total": 169.3194582989736,
"count": 45464,
"self": 2.9779064409260627,
"children": {
"TorchPolicy.evaluate": {
"total": 166.34155185804752,
"count": 45464,
"self": 166.34155185804752
}
}
},
"workers": {
"total": 0.5117535280207903,
"count": 45464,
"self": 0.0,
"children": {
"worker_root": {
"total": 1021.641058862021,
"count": 45464,
"is_parallel": true,
"self": 529.0788227780256,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00485937999997077,
"count": 1,
"is_parallel": true,
"self": 0.0034436680000453634,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014157119999254064,
"count": 10,
"is_parallel": true,
"self": 0.0014157119999254064
}
}
},
"UnityEnvironment.step": {
"total": 0.03939376399989669,
"count": 1,
"is_parallel": true,
"self": 0.0006052129997442535,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003683400000227266,
"count": 1,
"is_parallel": true,
"self": 0.0003683400000227266
},
"communicator.exchange": {
"total": 0.03488695600003666,
"count": 1,
"is_parallel": true,
"self": 0.03488695600003666
},
"steps_from_proto": {
"total": 0.0035332550000930496,
"count": 1,
"is_parallel": true,
"self": 0.0003657350000594306,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003167520000033619,
"count": 10,
"is_parallel": true,
"self": 0.003167520000033619
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 492.56223608399546,
"count": 45463,
"is_parallel": true,
"self": 23.930463065994218,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 13.010610195986374,
"count": 45463,
"is_parallel": true,
"self": 13.010610195986374
},
"communicator.exchange": {
"total": 378.96978444700676,
"count": 45463,
"is_parallel": true,
"self": 378.96978444700676
},
"steps_from_proto": {
"total": 76.65137837500811,
"count": 45463,
"is_parallel": true,
"self": 13.543614541996703,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.107763833011404,
"count": 454630,
"is_parallel": true,
"self": 63.107763833011404
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 290.3122693599769,
"count": 45464,
"self": 0.9312914639924657,
"children": {
"process_trajectory": {
"total": 63.056114528984835,
"count": 45464,
"self": 62.077113354985386,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9790011739994497,
"count": 10,
"self": 0.9790011739994497
}
}
},
"_update_policy": {
"total": 226.32486336699958,
"count": 47,
"self": 94.15127693900081,
"children": {
"TorchPPOOptimizer.update": {
"total": 132.17358642799877,
"count": 11460,
"self": 132.17358642799877
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.059999683813658e-07,
"count": 1,
"self": 9.059999683813658e-07
},
"TrainerController._save_models": {
"total": 0.07766683899990312,
"count": 1,
"self": 0.0007499429998460982,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07691689600005702,
"count": 1,
"self": 0.07691689600005702
}
}
}
}
}
}
}