sal-ops's picture
First Push
a4b48d1
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.059066653251648,
"min": 1.059066653251648,
"max": 2.8574273586273193,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10146.91796875,
"min": 10146.91796875,
"max": 29294.345703125,
"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": 11.975786209106445,
"min": 0.37341392040252686,
"max": 11.975786209106445,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2335.2783203125,
"min": 72.44229888916016,
"max": 2426.279296875,
"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": 0.07549378245787065,
"min": 0.06510582022282167,
"max": 0.07549378245787065,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3019751298314826,
"min": 0.26371991367697917,
"max": 0.3773268951048451,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19574001329202279,
"min": 0.11157201668224755,
"max": 0.2709583061582902,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7829600531680911,
"min": 0.4462880667289902,
"max": 1.2967481805997738,
"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": 23.34090909090909,
"min": 3.409090909090909,
"max": 24.10909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1027.0,
"min": 150.0,
"max": 1326.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.34090909090909,
"min": 3.409090909090909,
"max": 24.10909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1027.0,
"min": 150.0,
"max": 1326.0,
"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": "1699995907",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1699996372"
},
"total": 464.7527888809999,
"count": 1,
"self": 0.4254341929998873,
"children": {
"run_training.setup": {
"total": 0.04220237699996687,
"count": 1,
"self": 0.04220237699996687
},
"TrainerController.start_learning": {
"total": 464.28515231100005,
"count": 1,
"self": 0.520658753005705,
"children": {
"TrainerController._reset_env": {
"total": 9.102359632000002,
"count": 1,
"self": 9.102359632000002
},
"TrainerController.advance": {
"total": 454.5773342319942,
"count": 18207,
"self": 0.256249250000792,
"children": {
"env_step": {
"total": 454.3210849819934,
"count": 18207,
"self": 315.85316975499654,
"children": {
"SubprocessEnvManager._take_step": {
"total": 138.19917944600388,
"count": 18207,
"self": 1.3771429110116742,
"children": {
"TorchPolicy.evaluate": {
"total": 136.8220365349922,
"count": 18207,
"self": 136.8220365349922
}
}
},
"workers": {
"total": 0.26873578099298356,
"count": 18207,
"self": 0.0,
"children": {
"worker_root": {
"total": 463.02385361798565,
"count": 18207,
"is_parallel": true,
"self": 225.59221648297068,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006312072000014268,
"count": 1,
"is_parallel": true,
"self": 0.004973687999950016,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013383840000642522,
"count": 10,
"is_parallel": true,
"self": 0.0013383840000642522
}
}
},
"UnityEnvironment.step": {
"total": 0.05170531300007042,
"count": 1,
"is_parallel": true,
"self": 0.0006214779999709208,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00031180899998162204,
"count": 1,
"is_parallel": true,
"self": 0.00031180899998162204
},
"communicator.exchange": {
"total": 0.04894162100003996,
"count": 1,
"is_parallel": true,
"self": 0.04894162100003996
},
"steps_from_proto": {
"total": 0.001830405000077917,
"count": 1,
"is_parallel": true,
"self": 0.0003659370000832496,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014644679999946675,
"count": 10,
"is_parallel": true,
"self": 0.0014644679999946675
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 237.43163713501497,
"count": 18206,
"is_parallel": true,
"self": 10.239711106034633,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.17359131897274,
"count": 18206,
"is_parallel": true,
"self": 5.17359131897274
},
"communicator.exchange": {
"total": 189.7629863809991,
"count": 18206,
"is_parallel": true,
"self": 189.7629863809991
},
"steps_from_proto": {
"total": 32.255348329008484,
"count": 18206,
"is_parallel": true,
"self": 5.949574221016292,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.305774107992193,
"count": 182060,
"is_parallel": true,
"self": 26.305774107992193
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011387800009288185,
"count": 1,
"self": 0.00011387800009288185,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 451.0487233799829,
"count": 462225,
"is_parallel": true,
"self": 9.374045371933107,
"children": {
"process_trajectory": {
"total": 253.85856933405023,
"count": 462225,
"is_parallel": true,
"self": 253.02068114205042,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8378881919998094,
"count": 4,
"is_parallel": true,
"self": 0.8378881919998094
}
}
},
"_update_policy": {
"total": 187.81610867399957,
"count": 90,
"is_parallel": true,
"self": 63.03361552900435,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.78249314499521,
"count": 4587,
"is_parallel": true,
"self": 124.78249314499521
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08468581600004654,
"count": 1,
"self": 0.0008485590001328092,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08383725699991373,
"count": 1,
"self": 0.08383725699991373
}
}
}
}
}
}
}