Jerwinrand's picture
First Push
1b7bf0a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8009851574897766,
"min": 0.7911959290504456,
"max": 2.868342876434326,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7612.56298828125,
"min": 7612.56298828125,
"max": 29280.04296875,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.194398880004883,
"min": 0.23562657833099365,
"max": 13.194398880004883,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2572.90771484375,
"min": 45.71155548095703,
"max": 2680.05322265625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06759628342400652,
"min": 0.06139321122495234,
"max": 0.07208733402756694,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27038513369602607,
"min": 0.24557284489980935,
"max": 0.3604366701378347,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18899611957079054,
"min": 0.10983796067896537,
"max": 0.2920287071782,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7559844782831622,
"min": 0.4393518427158615,
"max": 1.455590943203253,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.568181818181817,
"min": 3.090909090909091,
"max": 26.054545454545455,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1125.0,
"min": 136.0,
"max": 1433.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.568181818181817,
"min": 3.090909090909091,
"max": 26.054545454545455,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1125.0,
"min": 136.0,
"max": 1433.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1743636727",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1743637211"
},
"total": 484.37061789099994,
"count": 1,
"self": 0.4877409739998484,
"children": {
"run_training.setup": {
"total": 0.024044658999969215,
"count": 1,
"self": 0.024044658999969215
},
"TrainerController.start_learning": {
"total": 483.8588322580001,
"count": 1,
"self": 0.499780778994932,
"children": {
"TrainerController._reset_env": {
"total": 3.184274797999933,
"count": 1,
"self": 3.184274797999933
},
"TrainerController.advance": {
"total": 480.08115016900535,
"count": 18192,
"self": 0.49087671700795,
"children": {
"env_step": {
"total": 344.34769059500195,
"count": 18192,
"self": 262.8020598280134,
"children": {
"SubprocessEnvManager._take_step": {
"total": 81.25449458100422,
"count": 18192,
"self": 1.5049460169964277,
"children": {
"TorchPolicy.evaluate": {
"total": 79.7495485640078,
"count": 18192,
"self": 79.7495485640078
}
}
},
"workers": {
"total": 0.2911361859843282,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 482.03626411100674,
"count": 18192,
"is_parallel": true,
"self": 252.39714678500968,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005414937999944414,
"count": 1,
"is_parallel": true,
"self": 0.003874387999871942,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015405500000724714,
"count": 10,
"is_parallel": true,
"self": 0.0015405500000724714
}
}
},
"UnityEnvironment.step": {
"total": 0.03679908699996304,
"count": 1,
"is_parallel": true,
"self": 0.00059688399994684,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004415180000023611,
"count": 1,
"is_parallel": true,
"self": 0.0004415180000023611
},
"communicator.exchange": {
"total": 0.033881097000062255,
"count": 1,
"is_parallel": true,
"self": 0.033881097000062255
},
"steps_from_proto": {
"total": 0.0018795879999515819,
"count": 1,
"is_parallel": true,
"self": 0.0003573810001853417,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015222069997662402,
"count": 10,
"is_parallel": true,
"self": 0.0015222069997662402
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 229.63911732599706,
"count": 18191,
"is_parallel": true,
"self": 10.481617642007791,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.883328894993724,
"count": 18191,
"is_parallel": true,
"self": 5.883328894993724
},
"communicator.exchange": {
"total": 179.36171470899683,
"count": 18191,
"is_parallel": true,
"self": 179.36171470899683
},
"steps_from_proto": {
"total": 33.91245607999872,
"count": 18191,
"is_parallel": true,
"self": 6.540239781013042,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.372216298985677,
"count": 181910,
"is_parallel": true,
"self": 27.372216298985677
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 135.24258285699545,
"count": 18192,
"self": 0.6973537779904291,
"children": {
"process_trajectory": {
"total": 29.333182844005364,
"count": 18192,
"self": 28.700100386005147,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6330824580002172,
"count": 4,
"self": 0.6330824580002172
}
}
},
"_update_policy": {
"total": 105.21204623499966,
"count": 90,
"self": 42.26501281699814,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.947033418001524,
"count": 4587,
"self": 62.947033418001524
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0159999419556698e-06,
"count": 1,
"self": 1.0159999419556698e-06
},
"TrainerController._save_models": {
"total": 0.09362549599995873,
"count": 1,
"self": 0.0009814039999582747,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09264409200000046,
"count": 1,
"self": 0.09264409200000046
}
}
}
}
}
}
}