IMENMANSOUR's picture
First Push
3e999e0 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9369367361068726,
"min": 0.9369367361068726,
"max": 2.8715531826019287,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8935.5654296875,
"min": 8935.5654296875,
"max": 29407.576171875,
"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": 12.566040992736816,
"min": 0.17680051922798157,
"max": 12.566040992736816,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2450.3779296875,
"min": 34.29930114746094,
"max": 2522.7939453125,
"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": 0.07755272792475772,
"min": 0.05916407766555637,
"max": 0.07755272792475772,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.31021091169903087,
"min": 0.23665631066222548,
"max": 0.3678876474165258,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19806846501488312,
"min": 0.1262587168899949,
"max": 0.28302026011195835,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7922738600595325,
"min": 0.5050348675599796,
"max": 1.4151013005597919,
"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": 24.522727272727273,
"min": 3.4545454545454546,
"max": 24.836363636363636,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1079.0,
"min": 152.0,
"max": 1366.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.522727272727273,
"min": 3.4545454545454546,
"max": 24.836363636363636,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1079.0,
"min": 152.0,
"max": 1366.0,
"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": "1712858909",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1712859386"
},
"total": 476.802938661,
"count": 1,
"self": 0.6648989130000018,
"children": {
"run_training.setup": {
"total": 0.055522643000017524,
"count": 1,
"self": 0.055522643000017524
},
"TrainerController.start_learning": {
"total": 476.08251710499997,
"count": 1,
"self": 0.5932234219934571,
"children": {
"TrainerController._reset_env": {
"total": 2.692266813999936,
"count": 1,
"self": 2.692266813999936
},
"TrainerController.advance": {
"total": 472.6879008680065,
"count": 18198,
"self": 0.30459816301652154,
"children": {
"env_step": {
"total": 472.38330270499,
"count": 18198,
"self": 305.6146886799994,
"children": {
"SubprocessEnvManager._take_step": {
"total": 166.453422785998,
"count": 18198,
"self": 1.5917796780032631,
"children": {
"TorchPolicy.evaluate": {
"total": 164.86164310799472,
"count": 18198,
"self": 164.86164310799472
}
}
},
"workers": {
"total": 0.31519123899261103,
"count": 18198,
"self": 0.0,
"children": {
"worker_root": {
"total": 474.6248341840105,
"count": 18198,
"is_parallel": true,
"self": 236.33697404701445,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00879007800006093,
"count": 1,
"is_parallel": true,
"self": 0.006383774000255471,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002406303999805459,
"count": 10,
"is_parallel": true,
"self": 0.002406303999805459
}
}
},
"UnityEnvironment.step": {
"total": 0.037286042999994606,
"count": 1,
"is_parallel": true,
"self": 0.0006447250000292115,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004271090000429467,
"count": 1,
"is_parallel": true,
"self": 0.0004271090000429467
},
"communicator.exchange": {
"total": 0.03423763999990115,
"count": 1,
"is_parallel": true,
"self": 0.03423763999990115
},
"steps_from_proto": {
"total": 0.0019765690000213,
"count": 1,
"is_parallel": true,
"self": 0.00038420399982896924,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015923650001923306,
"count": 10,
"is_parallel": true,
"self": 0.0015923650001923306
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 238.28786013699607,
"count": 18197,
"is_parallel": true,
"self": 10.847761577011966,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.8778590829931545,
"count": 18197,
"is_parallel": true,
"self": 5.8778590829931545
},
"communicator.exchange": {
"total": 184.59682054998837,
"count": 18197,
"is_parallel": true,
"self": 184.59682054998837
},
"steps_from_proto": {
"total": 36.96541892700259,
"count": 18197,
"is_parallel": true,
"self": 6.955807528005948,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.00961139899664,
"count": 181970,
"is_parallel": true,
"self": 30.00961139899664
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.3997000148010557e-05,
"count": 1,
"self": 4.3997000148010557e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 466.56919709304964,
"count": 716755,
"is_parallel": true,
"self": 15.504034351968699,
"children": {
"process_trajectory": {
"total": 257.79198998008076,
"count": 716755,
"is_parallel": true,
"self": 256.7019823170805,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0900076630002786,
"count": 4,
"is_parallel": true,
"self": 1.0900076630002786
}
}
},
"_update_policy": {
"total": 193.27317276100018,
"count": 90,
"is_parallel": true,
"self": 54.76345414199875,
"children": {
"TorchPPOOptimizer.update": {
"total": 138.50971861900143,
"count": 4584,
"is_parallel": true,
"self": 138.50971861900143
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10908200399990164,
"count": 1,
"self": 0.0011096229998202034,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10797238100008144,
"count": 1,
"self": 0.10797238100008144
}
}
}
}
}
}
}