adrian-nf's picture
initial commit
7a6d146 verified
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.2883284091949463,
"min": 2.2578766345977783,
"max": 2.370623826980591,
"count": 48
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 46645.28515625,
"min": 4697.43896484375,
"max": 49031.5625,
"count": 48
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 45.21495327102804,
"min": 33.9,
"max": 56.47126436781609,
"count": 48
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19352.0,
"min": 1356.0,
"max": 20012.0,
"count": 48
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1443.1159542453488,
"min": 1433.9323103201318,
"max": 1485.340514475233,
"count": 48
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 308826.8142085046,
"min": 29073.577677292353,
"max": 360355.0107725008,
"count": 48
},
"SoccerTwos.Step.mean": {
"value": 2999965.0,
"min": 2529953.0,
"max": 2999965.0,
"count": 48
},
"SoccerTwos.Step.sum": {
"value": 2999965.0,
"min": 2529953.0,
"max": 2999965.0,
"count": 48
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.07176772505044937,
"min": -0.14496664702892303,
"max": 0.09119022637605667,
"count": 48
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -15.358293533325195,
"min": -28.516891479492188,
"max": 20.791372299194336,
"count": 48
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.07692451030015945,
"min": -0.14932173490524292,
"max": 0.10056917369365692,
"count": 48
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -16.46184539794922,
"min": -29.037235260009766,
"max": 22.929771423339844,
"count": 48
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 48
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 48
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.11535233788401167,
"min": -0.4820842115502608,
"max": 0.1686799997375125,
"count": 48
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -24.685400307178497,
"min": -43.16159999370575,
"max": 35.422799944877625,
"count": 48
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.11535233788401167,
"min": -0.4820842115502608,
"max": 0.1686799997375125,
"count": 48
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -24.685400307178497,
"min": -43.16159999370575,
"max": 35.422799944877625,
"count": 48
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 48
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 48
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.01425742187226812,
"min": 0.012498459182097577,
"max": 0.022783190056604022,
"count": 22
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.01425742187226812,
"min": 0.012498459182097577,
"max": 0.022783190056604022,
"count": 22
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.10696341718236606,
"min": 0.09243139326572418,
"max": 0.11185142124692599,
"count": 22
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.10696341718236606,
"min": 0.09243139326572418,
"max": 0.11185142124692599,
"count": 22
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.10868611683448155,
"min": 0.09506866857409477,
"max": 0.11500879476467768,
"count": 22
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.10868611683448155,
"min": 0.09506866857409477,
"max": 0.11500879476467768,
"count": 22
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 22
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 22
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 22
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 22
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 22
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 22
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1734126925",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./train-soccer/SoccerTwos.yaml --env=train-soccer/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwosNew --no-graphics --resume",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1734129880"
},
"total": 2955.233237586999,
"count": 1,
"self": 0.009656171998358332,
"children": {
"run_training.setup": {
"total": 0.09122801299963612,
"count": 1,
"self": 0.09122801299963612
},
"TrainerController.start_learning": {
"total": 2955.132353402001,
"count": 1,
"self": 1.471143686088908,
"children": {
"TrainerController._reset_env": {
"total": 3.6418618119969324,
"count": 4,
"self": 3.6418618119969324
},
"TrainerController.advance": {
"total": 2949.8338889549123,
"count": 33661,
"self": 1.4734311612919555,
"children": {
"env_step": {
"total": 1088.3189411101412,
"count": 33661,
"self": 885.4894377948949,
"children": {
"SubprocessEnvManager._take_step": {
"total": 202.01222601794143,
"count": 33661,
"self": 7.401013266095106,
"children": {
"TorchPolicy.evaluate": {
"total": 194.61121275184632,
"count": 59406,
"self": 194.61121275184632
}
}
},
"workers": {
"total": 0.8172772973048268,
"count": 33661,
"self": 0.0,
"children": {
"worker_root": {
"total": 2946.748456279194,
"count": 33661,
"is_parallel": true,
"self": 2214.231777096149,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005093496998597402,
"count": 2,
"is_parallel": true,
"self": 0.0014661750028608367,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0036273219957365654,
"count": 8,
"is_parallel": true,
"self": 0.0036273219957365654
}
}
},
"UnityEnvironment.step": {
"total": 0.05034801800138666,
"count": 1,
"is_parallel": true,
"self": 0.0018442389991832897,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0011039829987566918,
"count": 1,
"is_parallel": true,
"self": 0.0011039829987566918
},
"communicator.exchange": {
"total": 0.04308805600157939,
"count": 1,
"is_parallel": true,
"self": 0.04308805600157939
},
"steps_from_proto": {
"total": 0.0043117400018672924,
"count": 2,
"is_parallel": true,
"self": 0.0007883020043664146,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003523437997500878,
"count": 8,
"is_parallel": true,
"self": 0.003523437997500878
}
}
}
}
}
}
},
"steps_from_proto": {
"total": 0.008853515999362571,
"count": 6,
"is_parallel": true,
"self": 0.0017533529935462866,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.007100163005816285,
"count": 24,
"is_parallel": true,
"self": 0.007100163005816285
}
}
},
"UnityEnvironment.step": {
"total": 732.5078256670458,
"count": 33660,
"is_parallel": true,
"self": 45.575933057818474,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 29.554295166686643,
"count": 33660,
"is_parallel": true,
"self": 29.554295166686643
},
"communicator.exchange": {
"total": 516.8730777226519,
"count": 33660,
"is_parallel": true,
"self": 516.8730777226519
},
"steps_from_proto": {
"total": 140.50451971988878,
"count": 67320,
"is_parallel": true,
"self": 25.433041058575327,
"children": {
"_process_rank_one_or_two_observation": {
"total": 115.07147866131345,
"count": 269280,
"is_parallel": true,
"self": 115.07147866131345
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1860.0415166834791,
"count": 33661,
"self": 9.422440332229598,
"children": {
"process_trajectory": {
"total": 300.6208975172449,
"count": 33661,
"self": 300.20648151024216,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4144160070027283,
"count": 1,
"self": 0.4144160070027283
}
}
},
"_update_policy": {
"total": 1549.9981788340046,
"count": 23,
"self": 93.86972147709457,
"children": {
"TorchPOCAOptimizer.update": {
"total": 1456.12845735691,
"count": 661,
"self": 1456.12845735691
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4210017980076373e-06,
"count": 1,
"self": 1.4210017980076373e-06
},
"TrainerController._save_models": {
"total": 0.18545752800127957,
"count": 1,
"self": 0.0033703480003168806,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1820871800009627,
"count": 1,
"self": 0.1820871800009627
}
}
}
}
}
}
}