torkable's picture
First Push
c474413 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.789191722869873,
"min": 1.789191722869873,
"max": 2.8902950286865234,
"count": 25
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 17004.478515625,
"min": 17004.478515625,
"max": 29615.80078125,
"count": 25
},
"SnowballTarget.Step.mean": {
"value": 249944.0,
"min": 9952.0,
"max": 249944.0,
"count": 25
},
"SnowballTarget.Step.sum": {
"value": 249944.0,
"min": 9952.0,
"max": 249944.0,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 7.599949359893799,
"min": -0.08250587433576584,
"max": 7.599949359893799,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1474.39013671875,
"min": -16.006139755249023,
"max": 1503.607666015625,
"count": 25
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 25
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 25
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 18.75,
"min": 3.090909090909091,
"max": 18.75,
"count": 25
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 825.0,
"min": 136.0,
"max": 1019.0,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 18.75,
"min": 3.090909090909091,
"max": 18.75,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 825.0,
"min": 136.0,
"max": 1019.0,
"count": 25
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 25
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 25
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.03527886943071887,
"min": 0.030246408036327922,
"max": 0.0401876058008167,
"count": 23
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.03527886943071887,
"min": 0.030246408036327922,
"max": 0.0401876058008167,
"count": 23
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2950232945382595,
"min": 0.10406746265907137,
"max": 0.3107394211822086,
"count": 23
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.2950232945382595,
"min": 0.10406746265907137,
"max": 0.3107394211822086,
"count": 23
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.1395296201600006e-05,
"min": 1.1395296201600006e-05,
"max": 0.00028690560436479975,
"count": 23
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.1395296201600006e-05,
"min": 1.1395296201600006e-05,
"max": 0.00028690560436479975,
"count": 23
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10379840000000001,
"min": 0.10379840000000001,
"max": 0.1956352,
"count": 23
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10379840000000001,
"min": 0.10379840000000001,
"max": 0.1956352,
"count": 23
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00019954016000000012,
"min": 0.00019954016000000012,
"max": 0.00478219648,
"count": 23
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00019954016000000012,
"min": 0.00019954016000000012,
"max": 0.00478219648,
"count": 23
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1736902020",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"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": "1736902443"
},
"total": 422.5819085000003,
"count": 1,
"self": 0.2733144070007256,
"children": {
"run_training.setup": {
"total": 0.058585615000083635,
"count": 1,
"self": 0.058585615000083635
},
"TrainerController.start_learning": {
"total": 422.2500084779995,
"count": 1,
"self": 0.4482569490101014,
"children": {
"TrainerController._reset_env": {
"total": 1.9245254690004003,
"count": 1,
"self": 1.9245254690004003
},
"TrainerController.advance": {
"total": 419.79398189898893,
"count": 22728,
"self": 0.433356283012472,
"children": {
"env_step": {
"total": 327.2681282119702,
"count": 22728,
"self": 245.65888422298485,
"children": {
"SubprocessEnvManager._take_step": {
"total": 81.3326250000182,
"count": 22728,
"self": 1.4879975199401088,
"children": {
"TorchPolicy.evaluate": {
"total": 79.84462748007809,
"count": 22728,
"self": 79.84462748007809
}
}
},
"workers": {
"total": 0.27661898896712955,
"count": 22728,
"self": 0.0,
"children": {
"worker_root": {
"total": 421.3764548870513,
"count": 22728,
"is_parallel": true,
"self": 206.0763834820391,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0023071309997249045,
"count": 1,
"is_parallel": true,
"self": 0.0006795179997425294,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016276129999823752,
"count": 10,
"is_parallel": true,
"self": 0.0016276129999823752
}
}
},
"UnityEnvironment.step": {
"total": 0.025460261000262108,
"count": 1,
"is_parallel": true,
"self": 0.00041130699992208974,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00030584700016333954,
"count": 1,
"is_parallel": true,
"self": 0.00030584700016333954
},
"communicator.exchange": {
"total": 0.023485920999519294,
"count": 1,
"is_parallel": true,
"self": 0.023485920999519294
},
"steps_from_proto": {
"total": 0.0012571860006573843,
"count": 1,
"is_parallel": true,
"self": 0.0002733550008997554,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009838309997576289,
"count": 10,
"is_parallel": true,
"self": 0.0009838309997576289
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 215.3000714050122,
"count": 22727,
"is_parallel": true,
"self": 7.869081381792967,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.163142427073581,
"count": 22727,
"is_parallel": true,
"self": 4.163142427073581
},
"communicator.exchange": {
"total": 177.15778599903206,
"count": 22727,
"is_parallel": true,
"self": 177.15778599903206
},
"steps_from_proto": {
"total": 26.1100615971136,
"count": 22727,
"is_parallel": true,
"self": 5.089790242698655,
"children": {
"_process_rank_one_or_two_observation": {
"total": 21.020271354414945,
"count": 227270,
"is_parallel": true,
"self": 21.020271354414945
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 92.09249740400628,
"count": 22728,
"self": 0.5154105560359312,
"children": {
"process_trajectory": {
"total": 30.377156392969482,
"count": 22728,
"self": 29.92112376796922,
"children": {
"RLTrainer._checkpoint": {
"total": 0.45603262500026176,
"count": 5,
"self": 0.45603262500026176
}
}
},
"_update_policy": {
"total": 61.19993045500087,
"count": 23,
"self": 41.19447367700013,
"children": {
"TorchPPOOptimizer.update": {
"total": 20.005456778000735,
"count": 1398,
"self": 20.005456778000735
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.830000635702163e-07,
"count": 1,
"self": 9.830000635702163e-07
},
"TrainerController._save_models": {
"total": 0.08324317799997516,
"count": 1,
"self": 0.0011110429995824234,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08213213500039274,
"count": 1,
"self": 0.08213213500039274
}
}
}
}
}
}
}