admarcosai's picture
First SnowballTarget push
57e28f9
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8386090397834778,
"min": 0.8297216892242432,
"max": 2.86547589302063,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7997.814453125,
"min": 7997.814453125,
"max": 29345.337890625,
"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": 12.874731063842773,
"min": 0.39602306485176086,
"max": 12.882061004638672,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2510.572509765625,
"min": 76.82847595214844,
"max": 2627.9404296875,
"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": 0.06875660025716392,
"min": 0.05878704695351189,
"max": 0.07425341044404823,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27502640102865566,
"min": 0.23514818781404756,
"max": 0.35741224661857507,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19811748563512865,
"min": 0.11565850980525069,
"max": 0.2856007335232753,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7924699425405146,
"min": 0.46263403922100277,
"max": 1.3796885510285697,
"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": 25.136363636363637,
"min": 3.2045454545454546,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1106.0,
"min": 141.0,
"max": 1399.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.136363636363637,
"min": 3.2045454545454546,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1106.0,
"min": 141.0,
"max": 1399.0,
"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": "1673975481",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1673975899"
},
"total": 418.15726196699995,
"count": 1,
"self": 0.38787008799999967,
"children": {
"run_training.setup": {
"total": 0.10649985299994569,
"count": 1,
"self": 0.10649985299994569
},
"TrainerController.start_learning": {
"total": 417.662892026,
"count": 1,
"self": 0.4807022160031238,
"children": {
"TrainerController._reset_env": {
"total": 9.61860631500008,
"count": 1,
"self": 9.61860631500008
},
"TrainerController.advance": {
"total": 407.4409783099968,
"count": 18201,
"self": 0.24454267199826063,
"children": {
"env_step": {
"total": 407.19643563799855,
"count": 18201,
"self": 265.2328366189977,
"children": {
"SubprocessEnvManager._take_step": {
"total": 141.7147622979994,
"count": 18201,
"self": 1.298341075990038,
"children": {
"TorchPolicy.evaluate": {
"total": 140.41642122200938,
"count": 18201,
"self": 30.427618448012595,
"children": {
"TorchPolicy.sample_actions": {
"total": 109.98880277399678,
"count": 18201,
"self": 109.98880277399678
}
}
}
}
},
"workers": {
"total": 0.24883672100145304,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 416.53409554400685,
"count": 18201,
"is_parallel": true,
"self": 203.88336783301065,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0058779229999572635,
"count": 1,
"is_parallel": true,
"self": 0.003612925000084033,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022649979998732306,
"count": 10,
"is_parallel": true,
"self": 0.0022649979998732306
}
}
},
"UnityEnvironment.step": {
"total": 0.032089573000007476,
"count": 1,
"is_parallel": true,
"self": 0.0005031429999462489,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003654629999800818,
"count": 1,
"is_parallel": true,
"self": 0.0003654629999800818
},
"communicator.exchange": {
"total": 0.029253922000066268,
"count": 1,
"is_parallel": true,
"self": 0.029253922000066268
},
"steps_from_proto": {
"total": 0.0019670450000148776,
"count": 1,
"is_parallel": true,
"self": 0.00046041099983540335,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015066340001794742,
"count": 10,
"is_parallel": true,
"self": 0.0015066340001794742
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 212.6507277109962,
"count": 18200,
"is_parallel": true,
"self": 8.197081450991845,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.972574279014793,
"count": 18200,
"is_parallel": true,
"self": 4.972574279014793
},
"communicator.exchange": {
"total": 167.61129307200156,
"count": 18200,
"is_parallel": true,
"self": 167.61129307200156
},
"steps_from_proto": {
"total": 31.869778908987996,
"count": 18200,
"is_parallel": true,
"self": 6.281812409003123,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.587966499984873,
"count": 182000,
"is_parallel": true,
"self": 25.587966499984873
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.088299999693845e-05,
"count": 1,
"self": 4.088299999693845e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 404.7234629940041,
"count": 322173,
"is_parallel": true,
"self": 8.283117180005775,
"children": {
"process_trajectory": {
"total": 231.0472237969983,
"count": 322173,
"is_parallel": true,
"self": 230.37990748299842,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6673163139998906,
"count": 4,
"is_parallel": true,
"self": 0.6673163139998906
}
}
},
"_update_policy": {
"total": 165.393122017,
"count": 90,
"is_parallel": true,
"self": 43.04625184900294,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.34687016799705,
"count": 4587,
"is_parallel": true,
"self": 122.34687016799705
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12256430200000068,
"count": 1,
"self": 0.0008341970000174115,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12173010499998327,
"count": 1,
"self": 0.12173010499998327
}
}
}
}
}
}
}