Ransaka's picture
First Push
6911193
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9038195610046387,
"min": 0.8881407380104065,
"max": 2.8702845573425293,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8629.6689453125,
"min": 8629.6689453125,
"max": 29394.583984375,
"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": 12.584139823913574,
"min": 0.371595174074173,
"max": 12.591764450073242,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2453.9072265625,
"min": 72.08946228027344,
"max": 2575.57470703125,
"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.Losses.PolicyLoss.mean": {
"value": 0.06887454741880385,
"min": 0.06059229312385843,
"max": 0.0743054238994898,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2754981896752154,
"min": 0.24236917249543372,
"max": 0.371527119497449,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.211949678101376,
"min": 0.13670268254217635,
"max": 0.29484794104800505,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.847798712405504,
"min": 0.5468107301687054,
"max": 1.4742397052400251,
"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.CumulativeReward.mean": {
"value": 24.886363636363637,
"min": 3.7045454545454546,
"max": 25.036363636363635,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1095.0,
"min": 163.0,
"max": 1377.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.886363636363637,
"min": 3.7045454545454546,
"max": 25.036363636363635,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1095.0,
"min": 163.0,
"max": 1377.0,
"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": "1676193541",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1676194002"
},
"total": 460.8128866699999,
"count": 1,
"self": 0.4376352259997702,
"children": {
"run_training.setup": {
"total": 0.11194252400002824,
"count": 1,
"self": 0.11194252400002824
},
"TrainerController.start_learning": {
"total": 460.2633089200001,
"count": 1,
"self": 0.5368983749996232,
"children": {
"TrainerController._reset_env": {
"total": 9.536735225999905,
"count": 1,
"self": 9.536735225999905
},
"TrainerController.advance": {
"total": 450.06874941100045,
"count": 18202,
"self": 0.2703106050017823,
"children": {
"env_step": {
"total": 449.79843880599867,
"count": 18202,
"self": 308.19399563599086,
"children": {
"SubprocessEnvManager._take_step": {
"total": 141.33549969500393,
"count": 18202,
"self": 1.459237910006891,
"children": {
"TorchPolicy.evaluate": {
"total": 139.87626178499704,
"count": 18202,
"self": 31.675618794989646,
"children": {
"TorchPolicy.sample_actions": {
"total": 108.2006429900074,
"count": 18202,
"self": 108.2006429900074
}
}
}
}
},
"workers": {
"total": 0.26894347500387994,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 458.82230118098573,
"count": 18202,
"is_parallel": true,
"self": 221.62710409098543,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006129099000077076,
"count": 1,
"is_parallel": true,
"self": 0.0036041289998820503,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002524970000195026,
"count": 10,
"is_parallel": true,
"self": 0.002524970000195026
}
}
},
"UnityEnvironment.step": {
"total": 0.046213728999987325,
"count": 1,
"is_parallel": true,
"self": 0.00042017599992050236,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00034044899996388267,
"count": 1,
"is_parallel": true,
"self": 0.00034044899996388267
},
"communicator.exchange": {
"total": 0.04351278900003308,
"count": 1,
"is_parallel": true,
"self": 0.04351278900003308
},
"steps_from_proto": {
"total": 0.0019403150000698588,
"count": 1,
"is_parallel": true,
"self": 0.00040355500004807254,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015367600000217863,
"count": 10,
"is_parallel": true,
"self": 0.0015367600000217863
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 237.1951970900003,
"count": 18201,
"is_parallel": true,
"self": 9.631370105985752,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.072121164998293,
"count": 18201,
"is_parallel": true,
"self": 5.072121164998293
},
"communicator.exchange": {
"total": 190.82795516801355,
"count": 18201,
"is_parallel": true,
"self": 190.82795516801355
},
"steps_from_proto": {
"total": 31.663750651002715,
"count": 18201,
"is_parallel": true,
"self": 6.837582776979275,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.82616787402344,
"count": 182010,
"is_parallel": true,
"self": 24.82616787402344
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012207500003569294,
"count": 1,
"self": 0.00012207500003569294,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 446.76167240396705,
"count": 392396,
"is_parallel": true,
"self": 10.170786077960315,
"children": {
"process_trajectory": {
"total": 254.5708386080072,
"count": 392396,
"is_parallel": true,
"self": 253.4555696820073,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1152689259998851,
"count": 4,
"is_parallel": true,
"self": 1.1152689259998851
}
}
},
"_update_policy": {
"total": 182.02004771799955,
"count": 90,
"is_parallel": true,
"self": 59.9477394689975,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.07230824900205,
"count": 4587,
"is_parallel": true,
"self": 122.07230824900205
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1208038330000818,
"count": 1,
"self": 0.0008833300000787858,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11992050300000301,
"count": 1,
"self": 0.11992050300000301
}
}
}
}
}
}
}