Kedar1977's picture
First Push
c52dc4b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9540029764175415,
"min": 0.9540029764175415,
"max": 2.8722774982452393,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9129.80859375,
"min": 9129.80859375,
"max": 29478.18359375,
"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": 12.924789428710938,
"min": 0.24149367213249207,
"max": 12.924789428710938,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2520.333984375,
"min": 46.84977340698242,
"max": 2632.501220703125,
"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": 0.06524869460868193,
"min": 0.0622550310516803,
"max": 0.07753462898236808,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26099477843472774,
"min": 0.25858781953095733,
"max": 0.35576979609322734,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21914536053059147,
"min": 0.10795853643532038,
"max": 0.2938974468293143,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8765814421223659,
"min": 0.43183414574128154,
"max": 1.385111935874995,
"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": 3.022727272727273,
"max": 25.69090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1095.0,
"min": 133.0,
"max": 1413.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.886363636363637,
"min": 3.022727272727273,
"max": 25.69090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1095.0,
"min": 133.0,
"max": 1413.0,
"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": "1729316929",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1729317542"
},
"total": 613.2135041410002,
"count": 1,
"self": 0.5423372020002262,
"children": {
"run_training.setup": {
"total": 0.07853198099996916,
"count": 1,
"self": 0.07853198099996916
},
"TrainerController.start_learning": {
"total": 612.592634958,
"count": 1,
"self": 0.8740800090149605,
"children": {
"TrainerController._reset_env": {
"total": 6.606555105999973,
"count": 1,
"self": 6.606555105999973
},
"TrainerController.advance": {
"total": 605.0216693599854,
"count": 18203,
"self": 0.46019737599203836,
"children": {
"env_step": {
"total": 604.5614719839933,
"count": 18203,
"self": 460.2172508020029,
"children": {
"SubprocessEnvManager._take_step": {
"total": 143.9054202610081,
"count": 18203,
"self": 2.630214592012635,
"children": {
"TorchPolicy.evaluate": {
"total": 141.27520566899545,
"count": 18203,
"self": 141.27520566899545
}
}
},
"workers": {
"total": 0.4388009209823167,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 610.6988529269873,
"count": 18203,
"is_parallel": true,
"self": 294.73969633500883,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0033717200000182856,
"count": 1,
"is_parallel": true,
"self": 0.001092514000220035,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022792059997982506,
"count": 10,
"is_parallel": true,
"self": 0.0022792059997982506
}
}
},
"UnityEnvironment.step": {
"total": 0.046488896000028035,
"count": 1,
"is_parallel": true,
"self": 0.0008410079999521258,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004678900000953945,
"count": 1,
"is_parallel": true,
"self": 0.0004678900000953945
},
"communicator.exchange": {
"total": 0.04280678400004945,
"count": 1,
"is_parallel": true,
"self": 0.04280678400004945
},
"steps_from_proto": {
"total": 0.0023732139999310675,
"count": 1,
"is_parallel": true,
"self": 0.00046897599997919315,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019042379999518744,
"count": 10,
"is_parallel": true,
"self": 0.0019042379999518744
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 315.9591565919785,
"count": 18202,
"is_parallel": true,
"self": 15.25639208695577,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.549469573010811,
"count": 18202,
"is_parallel": true,
"self": 7.549469573010811
},
"communicator.exchange": {
"total": 248.1839771920146,
"count": 18202,
"is_parallel": true,
"self": 248.1839771920146
},
"steps_from_proto": {
"total": 44.96931773999734,
"count": 18202,
"is_parallel": true,
"self": 8.96949572795495,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.99982201204239,
"count": 182020,
"is_parallel": true,
"self": 35.99982201204239
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001870059998054785,
"count": 1,
"self": 0.0001870059998054785,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 597.9469777688907,
"count": 779949,
"is_parallel": true,
"self": 18.561259413960784,
"children": {
"process_trajectory": {
"total": 321.56137950593063,
"count": 779949,
"is_parallel": true,
"self": 320.8457663049305,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7156132010001102,
"count": 4,
"is_parallel": true,
"self": 0.7156132010001102
}
}
},
"_update_policy": {
"total": 257.82433884899933,
"count": 90,
"is_parallel": true,
"self": 75.7081975910013,
"children": {
"TorchPPOOptimizer.update": {
"total": 182.11614125799804,
"count": 4584,
"is_parallel": true,
"self": 182.11614125799804
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09014347699985592,
"count": 1,
"self": 0.0012498039998263266,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0888936730000296,
"count": 1,
"self": 0.0888936730000296
}
}
}
}
}
}
}