nhiro3303's picture
First Push
07c5d22
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.124293327331543,
"min": 2.124293327331543,
"max": 2.8902509212493896,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 20376.220703125,
"min": 20282.0859375,
"max": 29756.390625,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 8.391050338745117,
"min": 0.30387070775032043,
"max": 8.391050338745117,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1720.165283203125,
"min": 58.9509162902832,
"max": 1720.165283203125,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 10.236363636363636,
"min": 2.2954545454545454,
"max": 10.236363636363636,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 563.0,
"min": 101.0,
"max": 563.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 10.236363636363636,
"min": 2.2954545454545454,
"max": 10.236363636363636,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 563.0,
"min": 101.0,
"max": 563.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.038265809407069654,
"min": 0.023547798260551644,
"max": 0.04320487544221881,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.07653161881413931,
"min": 0.04709559652110329,
"max": 0.10839927864314328,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.3306956458836794,
"min": 0.08900228406613073,
"max": 0.3937650366375844,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6613912917673588,
"min": 0.17800456813226145,
"max": 1.095505164315303,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.053789824000006e-07,
"min": 3.053789824000006e-07,
"max": 2.96092813024e-05,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 6.107579648000011e-07,
"min": 6.107579648000011e-07,
"max": 8.36798610672e-05,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1010176,
"min": 0.1010176,
"max": 0.19869760000000003,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.2020352,
"min": 0.2020352,
"max": 0.5789328,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.07782400000001e-05,
"min": 6.07782400000001e-05,
"max": 0.00493501024,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0001215564800000002,
"min": 0.0001215564800000002,
"max": 0.01394874672,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1676343732",
"python_version": "3.9.9 (main, Feb 14 2023, 11:37:38) \n[GCC 11.3.0]",
"command_line_arguments": "/home/gpu/venv/bin/mlagents-learn ./content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget --no-graphics --force",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.13.1+cu117",
"numpy_version": "1.19.0",
"end_time_seconds": "1676344538"
},
"total": 805.6091407479998,
"count": 1,
"self": 0.21926659299970197,
"children": {
"run_training.setup": {
"total": 0.01571043500007363,
"count": 1,
"self": 0.01571043500007363
},
"TrainerController.start_learning": {
"total": 805.3741637200001,
"count": 1,
"self": 0.6650652019516201,
"children": {
"TrainerController._reset_env": {
"total": 1.4157431909998195,
"count": 1,
"self": 1.4157431909998195
},
"TrainerController.advance": {
"total": 803.2314799490487,
"count": 45464,
"self": 0.609717984114468,
"children": {
"env_step": {
"total": 582.8458895140257,
"count": 45464,
"self": 402.59608837781525,
"children": {
"SubprocessEnvManager._take_step": {
"total": 179.8474327291251,
"count": 45464,
"self": 1.875769938976191,
"children": {
"TorchPolicy.evaluate": {
"total": 177.9716627901489,
"count": 45464,
"self": 66.33382042323956,
"children": {
"TorchPolicy.sample_actions": {
"total": 111.63784236690935,
"count": 45464,
"self": 111.63784236690935
}
}
}
}
},
"workers": {
"total": 0.4023684070853051,
"count": 45464,
"self": 0.0,
"children": {
"worker_root": {
"total": 803.5805384072983,
"count": 45464,
"is_parallel": true,
"self": 440.0725893512117,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0014014680000400404,
"count": 1,
"is_parallel": true,
"self": 0.00029258399899845244,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001108884001041588,
"count": 10,
"is_parallel": true,
"self": 0.001108884001041588
}
}
},
"UnityEnvironment.step": {
"total": 0.018407370999739214,
"count": 1,
"is_parallel": true,
"self": 0.00021916500008956064,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019756499932555016,
"count": 1,
"is_parallel": true,
"self": 0.00019756499932555016
},
"communicator.exchange": {
"total": 0.016939925000770018,
"count": 1,
"is_parallel": true,
"self": 0.016939925000770018
},
"steps_from_proto": {
"total": 0.001050715999554086,
"count": 1,
"is_parallel": true,
"self": 0.00018652599828783423,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008641900012662518,
"count": 10,
"is_parallel": true,
"self": 0.0008641900012662518
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 363.50794905608655,
"count": 45463,
"is_parallel": true,
"self": 9.405622356724962,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.104283027252677,
"count": 45463,
"is_parallel": true,
"self": 5.104283027252677
},
"communicator.exchange": {
"total": 302.6035683910013,
"count": 45463,
"is_parallel": true,
"self": 302.6035683910013
},
"steps_from_proto": {
"total": 46.39447528110759,
"count": 45463,
"is_parallel": true,
"self": 6.8725387337763095,
"children": {
"_process_rank_one_or_two_observation": {
"total": 39.52193654733128,
"count": 454630,
"is_parallel": true,
"self": 39.52193654733128
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 219.77587245090854,
"count": 45464,
"self": 0.7218836578867922,
"children": {
"process_trajectory": {
"total": 80.6871276650254,
"count": 45464,
"self": 80.00271182402503,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6844158410003729,
"count": 10,
"self": 0.6844158410003729
}
}
},
"_update_policy": {
"total": 138.36686112799634,
"count": 113,
"self": 94.2921326990172,
"children": {
"TorchPPOOptimizer.update": {
"total": 44.07472842897914,
"count": 2712,
"self": 44.07472842897914
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.700000423938036e-07,
"count": 1,
"self": 7.700000423938036e-07
},
"TrainerController._save_models": {
"total": 0.0618746079999255,
"count": 1,
"self": 0.00045164900075178593,
"children": {
"RLTrainer._checkpoint": {
"total": 0.061422958999173716,
"count": 1,
"self": 0.061422958999173716
}
}
}
}
}
}
}