Aedelon's picture
First Push
552497f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9332671761512756,
"min": 0.9332671761512756,
"max": 2.8534417152404785,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8900.5693359375,
"min": 8900.5693359375,
"max": 29222.095703125,
"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": 12.481861114501953,
"min": 0.4177608788013458,
"max": 12.481861114501953,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2433.962890625,
"min": 81.04560852050781,
"max": 2516.81982421875,
"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": 0.07065466268720817,
"min": 0.0648532755880653,
"max": 0.07594185028802695,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2826186507488327,
"min": 0.263009952708814,
"max": 0.3721249185972756,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19747052750751082,
"min": 0.13197460082272872,
"max": 0.2647702941123177,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7898821100300433,
"min": 0.5278984032909149,
"max": 1.3238514705615885,
"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": 3.4545454545454546,
"max": 25.045454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1095.0,
"min": 152.0,
"max": 1363.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.886363636363637,
"min": 3.4545454545454546,
"max": 25.045454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1095.0,
"min": 152.0,
"max": 1363.0,
"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": "1705060092",
"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=SnowballTarget2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1705060578"
},
"total": 485.901041264,
"count": 1,
"self": 0.4761612479996984,
"children": {
"run_training.setup": {
"total": 0.051129397000295285,
"count": 1,
"self": 0.051129397000295285
},
"TrainerController.start_learning": {
"total": 485.373750619,
"count": 1,
"self": 0.6617775430795518,
"children": {
"TrainerController._reset_env": {
"total": 3.756127091000053,
"count": 1,
"self": 3.756127091000053
},
"TrainerController.advance": {
"total": 480.855204025921,
"count": 18198,
"self": 0.29839100989283907,
"children": {
"env_step": {
"total": 480.5568130160282,
"count": 18198,
"self": 318.38558885501607,
"children": {
"SubprocessEnvManager._take_step": {
"total": 161.84731136408936,
"count": 18198,
"self": 1.5870615781141169,
"children": {
"TorchPolicy.evaluate": {
"total": 160.26024978597525,
"count": 18198,
"self": 160.26024978597525
}
}
},
"workers": {
"total": 0.3239127969227411,
"count": 18198,
"self": 0.0,
"children": {
"worker_root": {
"total": 484.0163482979606,
"count": 18198,
"is_parallel": true,
"self": 237.2564530690015,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0055265219998545945,
"count": 1,
"is_parallel": true,
"self": 0.003932509999685863,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001594012000168732,
"count": 10,
"is_parallel": true,
"self": 0.001594012000168732
}
}
},
"UnityEnvironment.step": {
"total": 0.07491239799946925,
"count": 1,
"is_parallel": true,
"self": 0.0006861859992568498,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004687910004577134,
"count": 1,
"is_parallel": true,
"self": 0.0004687910004577134
},
"communicator.exchange": {
"total": 0.07167415900039487,
"count": 1,
"is_parallel": true,
"self": 0.07167415900039487
},
"steps_from_proto": {
"total": 0.00208326199935982,
"count": 1,
"is_parallel": true,
"self": 0.0003853309999612975,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016979309993985225,
"count": 10,
"is_parallel": true,
"self": 0.0016979309993985225
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 246.75989522895907,
"count": 18197,
"is_parallel": true,
"self": 11.39709542491164,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.712598173994593,
"count": 18197,
"is_parallel": true,
"self": 5.712598173994593
},
"communicator.exchange": {
"total": 193.61967208601618,
"count": 18197,
"is_parallel": true,
"self": 193.61967208601618
},
"steps_from_proto": {
"total": 36.03052954403665,
"count": 18197,
"is_parallel": true,
"self": 6.755419884049843,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.27510965998681,
"count": 181970,
"is_parallel": true,
"self": 29.27510965998681
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00020561499968607677,
"count": 1,
"self": 0.00020561499968607677,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 474.82795725562755,
"count": 714449,
"is_parallel": true,
"self": 15.28007573537343,
"children": {
"process_trajectory": {
"total": 261.86597843725394,
"count": 714449,
"is_parallel": true,
"self": 261.3567435432533,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5092348940006559,
"count": 4,
"is_parallel": true,
"self": 0.5092348940006559
}
}
},
"_update_policy": {
"total": 197.68190308300018,
"count": 90,
"is_parallel": true,
"self": 61.46392691402161,
"children": {
"TorchPPOOptimizer.update": {
"total": 136.21797616897857,
"count": 4587,
"is_parallel": true,
"self": 136.21797616897857
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10043634399971779,
"count": 1,
"self": 0.001494601999183942,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09894174200053385,
"count": 1,
"self": 0.09894174200053385
}
}
}
}
}
}
}