kelvinksau's picture
First Push
685c53a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9608741998672485,
"min": 0.9600244760513306,
"max": 2.8558905124664307,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9132.1484375,
"min": 9132.1484375,
"max": 29152.9296875,
"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": 13.008769035339355,
"min": 0.4641377925872803,
"max": 13.126465797424316,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2536.7099609375,
"min": 90.04273223876953,
"max": 2677.799072265625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06872963589244047,
"min": 0.05866085796536508,
"max": 0.07187168517431893,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27491854356976186,
"min": 0.23464343186146033,
"max": 0.3570500708358618,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.232641134849366,
"min": 0.11916823186865988,
"max": 0.2963506878152782,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.930564539397464,
"min": 0.4766729274746395,
"max": 1.3530684738766914,
"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": 24.84090909090909,
"min": 3.2045454545454546,
"max": 26.045454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1093.0,
"min": 141.0,
"max": 1420.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.84090909090909,
"min": 3.2045454545454546,
"max": 26.045454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1093.0,
"min": 141.0,
"max": 1420.0,
"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": "1742186374",
"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": "1742186814"
},
"total": 439.21767062100014,
"count": 1,
"self": 0.4389468260000058,
"children": {
"run_training.setup": {
"total": 0.023966008000002148,
"count": 1,
"self": 0.023966008000002148
},
"TrainerController.start_learning": {
"total": 438.75475778700013,
"count": 1,
"self": 0.4267671689965482,
"children": {
"TrainerController._reset_env": {
"total": 2.9907601719999093,
"count": 1,
"self": 2.9907601719999093
},
"TrainerController.advance": {
"total": 435.2490648530039,
"count": 18192,
"self": 0.43640933297297124,
"children": {
"env_step": {
"total": 310.5467502120181,
"count": 18192,
"self": 236.45073172599837,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.86400259899597,
"count": 18192,
"self": 1.338525716985714,
"children": {
"TorchPolicy.evaluate": {
"total": 72.52547688201025,
"count": 18192,
"self": 72.52547688201025
}
}
},
"workers": {
"total": 0.2320158870237492,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 437.24515058900704,
"count": 18192,
"is_parallel": true,
"self": 230.7397144090063,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005765095000015208,
"count": 1,
"is_parallel": true,
"self": 0.00415265799995268,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016124370000625277,
"count": 10,
"is_parallel": true,
"self": 0.0016124370000625277
}
}
},
"UnityEnvironment.step": {
"total": 0.03442201200005002,
"count": 1,
"is_parallel": true,
"self": 0.0006046580000429458,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004055919999927937,
"count": 1,
"is_parallel": true,
"self": 0.0004055919999927937
},
"communicator.exchange": {
"total": 0.031444479000015235,
"count": 1,
"is_parallel": true,
"self": 0.031444479000015235
},
"steps_from_proto": {
"total": 0.0019672829999990427,
"count": 1,
"is_parallel": true,
"self": 0.00038555700029974105,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015817259996993016,
"count": 10,
"is_parallel": true,
"self": 0.0015817259996993016
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 206.50543618000074,
"count": 18191,
"is_parallel": true,
"self": 9.967619700970545,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.402684312012525,
"count": 18191,
"is_parallel": true,
"self": 5.402684312012525
},
"communicator.exchange": {
"total": 158.85002939002186,
"count": 18191,
"is_parallel": true,
"self": 158.85002939002186
},
"steps_from_proto": {
"total": 32.285102776995814,
"count": 18191,
"is_parallel": true,
"self": 6.001165072990716,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.283937704005098,
"count": 181910,
"is_parallel": true,
"self": 26.283937704005098
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.26590530801286,
"count": 18192,
"self": 0.5036319629936088,
"children": {
"process_trajectory": {
"total": 27.64438567101888,
"count": 18192,
"self": 27.164293558019153,
"children": {
"RLTrainer._checkpoint": {
"total": 0.48009211299972776,
"count": 4,
"self": 0.48009211299972776
}
}
},
"_update_policy": {
"total": 96.11788767400037,
"count": 90,
"self": 38.59029132800765,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.52759634599272,
"count": 4587,
"self": 57.52759634599272
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.109998361760518e-07,
"count": 1,
"self": 8.109998361760518e-07
},
"TrainerController._save_models": {
"total": 0.08816478199992162,
"count": 1,
"self": 0.0009861019998425036,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08717868000007911,
"count": 1,
"self": 0.08717868000007911
}
}
}
}
}
}
}