tux's picture
Second Push
eaa49ba
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6749759912490845,
"min": 0.6749759912490845,
"max": 0.8381103873252869,
"count": 13
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6459.5205078125,
"min": 6459.5205078125,
"max": 8555.4306640625,
"count": 13
},
"SnowballTarget.Step.mean": {
"value": 399944.0,
"min": 279992.0,
"max": 399944.0,
"count": 13
},
"SnowballTarget.Step.sum": {
"value": 399944.0,
"min": 279992.0,
"max": 399944.0,
"count": 13
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.998022079467773,
"min": 12.612207412719727,
"max": 13.121735572814941,
"count": 13
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2521.6162109375,
"min": 2397.19091796875,
"max": 2676.833984375,
"count": 13
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 13
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 13
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06842379256248059,
"min": 0.06274938085330445,
"max": 0.07379341599087497,
"count": 13
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27369517024992235,
"min": 0.2530691640870417,
"max": 0.36896707995437483,
"count": 13
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19016173211675066,
"min": 0.18351931782329783,
"max": 0.2117971901800118,
"count": 13
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7606469284670027,
"min": 0.7515429112256742,
"max": 1.058985950900059,
"count": 13
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 4.0230986590000025e-06,
"min": 4.0230986590000025e-06,
"max": 9.312306895899999e-05,
"count": 13
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.609239463600001e-05,
"min": 1.609239463600001e-05,
"max": 0.0003954903681699999,
"count": 13
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10134100000000001,
"min": 0.10134100000000001,
"max": 0.13104100000000002,
"count": 13
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.40536400000000006,
"min": 0.40536400000000006,
"max": 0.63183,
"count": 13
},
"SnowballTarget.Policy.Beta.mean": {
"value": 7.691590000000003e-05,
"min": 7.691590000000003e-05,
"max": 0.0015589459000000005,
"count": 13
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0003076636000000001,
"min": 0.0003076636000000001,
"max": 0.006628317,
"count": 13
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.681818181818183,
"min": 24.454545454545453,
"max": 26.022727272727273,
"count": 13
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1130.0,
"min": 1076.0,
"max": 1423.0,
"count": 13
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.681818181818183,
"min": 24.454545454545453,
"max": 26.022727272727273,
"count": 13
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1130.0,
"min": 1076.0,
"max": 1423.0,
"count": 13
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 13
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 13
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1687089213",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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 --resume",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1687089515"
},
"total": 302.4342371169996,
"count": 1,
"self": 0.8387473499997213,
"children": {
"run_training.setup": {
"total": 0.06620121099967946,
"count": 1,
"self": 0.06620121099967946
},
"TrainerController.start_learning": {
"total": 301.5292885560002,
"count": 1,
"self": 0.3744299729842169,
"children": {
"TrainerController._reset_env": {
"total": 4.302400324000246,
"count": 1,
"self": 4.302400324000246
},
"TrainerController.advance": {
"total": 296.62832749101517,
"count": 11821,
"self": 0.16391955803783276,
"children": {
"env_step": {
"total": 296.46440793297734,
"count": 11821,
"self": 218.3596087559531,
"children": {
"SubprocessEnvManager._take_step": {
"total": 77.9404431580283,
"count": 11821,
"self": 1.2103973100033727,
"children": {
"TorchPolicy.evaluate": {
"total": 76.73004584802493,
"count": 11821,
"self": 76.73004584802493
}
}
},
"workers": {
"total": 0.16435601899593166,
"count": 11821,
"self": 0.0,
"children": {
"worker_root": {
"total": 300.37892925197,
"count": 11821,
"is_parallel": true,
"self": 142.82830187891295,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003400146999865683,
"count": 1,
"is_parallel": true,
"self": 0.0007431369999721937,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0026570099998934893,
"count": 10,
"is_parallel": true,
"self": 0.0026570099998934893
}
}
},
"UnityEnvironment.step": {
"total": 0.04434941599993181,
"count": 1,
"is_parallel": true,
"self": 0.0005497960000866442,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00032860099963727407,
"count": 1,
"is_parallel": true,
"self": 0.00032860099963727407
},
"communicator.exchange": {
"total": 0.041253743000197574,
"count": 1,
"is_parallel": true,
"self": 0.041253743000197574
},
"steps_from_proto": {
"total": 0.0022172760000103153,
"count": 1,
"is_parallel": true,
"self": 0.0004083720004928182,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018089039995174971,
"count": 10,
"is_parallel": true,
"self": 0.0018089039995174971
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 157.55062737305707,
"count": 11820,
"is_parallel": true,
"self": 6.540792842022256,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.3528731100345794,
"count": 11820,
"is_parallel": true,
"self": 3.3528731100345794
},
"communicator.exchange": {
"total": 125.86504411401711,
"count": 11820,
"is_parallel": true,
"self": 125.86504411401711
},
"steps_from_proto": {
"total": 21.791917306983123,
"count": 11820,
"is_parallel": true,
"self": 3.9140963719200954,
"children": {
"_process_rank_one_or_two_observation": {
"total": 17.877820935063028,
"count": 118200,
"is_parallel": true,
"self": 17.877820935063028
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00018013600038102595,
"count": 1,
"self": 0.00018013600038102595,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 294.4034886741424,
"count": 275822,
"is_parallel": true,
"self": 6.150136907125216,
"children": {
"process_trajectory": {
"total": 160.87285804101384,
"count": 275822,
"is_parallel": true,
"self": 159.30715024501342,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5657077960004244,
"count": 3,
"is_parallel": true,
"self": 1.5657077960004244
}
}
},
"_update_policy": {
"total": 127.38049372600335,
"count": 58,
"is_parallel": true,
"self": 49.78196640102624,
"children": {
"TorchPPOOptimizer.update": {
"total": 77.59852732497711,
"count": 2955,
"is_parallel": true,
"self": 77.59852732497711
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2239506320001965,
"count": 1,
"self": 0.0018281009997735964,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2221225310004229,
"count": 1,
"self": 0.2221225310004229
}
}
}
}
}
}
}