ByteExplorer's picture
First Push
74c77d3
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9890428781509399,
"min": 0.9692286849021912,
"max": 2.8643295764923096,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9508.658203125,
"min": 9508.658203125,
"max": 29459.62890625,
"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": 12.041976928710938,
"min": 0.312862366437912,
"max": 12.041976928710938,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2348.185546875,
"min": 60.69529724121094,
"max": 2421.79296875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06905941159764588,
"min": 0.0637184276286765,
"max": 0.07654857261051945,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2762376463905835,
"min": 0.254873710514706,
"max": 0.36285360355395824,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21753805594555303,
"min": 0.10302229644274158,
"max": 0.27242677831182294,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8701522237822121,
"min": 0.4120891857709663,
"max": 1.3621338915591146,
"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": 23.863636363636363,
"min": 2.9318181818181817,
"max": 23.977272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1050.0,
"min": 129.0,
"max": 1299.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.863636363636363,
"min": 2.9318181818181817,
"max": 23.977272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1050.0,
"min": 129.0,
"max": 1299.0,
"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": "1689707086",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"command_line_arguments": "/home/arran/.local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1689707271"
},
"total": 184.54512175401032,
"count": 1,
"self": 0.21794814300665166,
"children": {
"run_training.setup": {
"total": 0.009685946002718993,
"count": 1,
"self": 0.009685946002718993
},
"TrainerController.start_learning": {
"total": 184.31748766500095,
"count": 1,
"self": 0.2535555436188588,
"children": {
"TrainerController._reset_env": {
"total": 2.474105157001759,
"count": 1,
"self": 2.474105157001759
},
"TrainerController.advance": {
"total": 181.51562136938446,
"count": 18209,
"self": 0.12030773251899518,
"children": {
"env_step": {
"total": 181.39531363686547,
"count": 18209,
"self": 131.65605812524154,
"children": {
"SubprocessEnvManager._take_step": {
"total": 49.61544951298856,
"count": 18209,
"self": 0.7191228498268174,
"children": {
"TorchPolicy.evaluate": {
"total": 48.896326663161744,
"count": 18209,
"self": 48.896326663161744
}
}
},
"workers": {
"total": 0.1238059986353619,
"count": 18209,
"self": 0.0,
"children": {
"worker_root": {
"total": 183.9796360952314,
"count": 18209,
"is_parallel": true,
"self": 98.11927624826785,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012240060023032129,
"count": 1,
"is_parallel": true,
"self": 0.00048465700820088387,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000739348994102329,
"count": 10,
"is_parallel": true,
"self": 0.000739348994102329
}
}
},
"UnityEnvironment.step": {
"total": 0.013724046002607793,
"count": 1,
"is_parallel": true,
"self": 0.00021589899552054703,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001663450093474239,
"count": 1,
"is_parallel": true,
"self": 0.0001663450093474239
},
"communicator.exchange": {
"total": 0.012626758994883858,
"count": 1,
"is_parallel": true,
"self": 0.012626758994883858
},
"steps_from_proto": {
"total": 0.000715043002855964,
"count": 1,
"is_parallel": true,
"self": 0.00015529400843661278,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005597489944193512,
"count": 10,
"is_parallel": true,
"self": 0.0005597489944193512
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 85.86035984696355,
"count": 18208,
"is_parallel": true,
"self": 3.9446354413666995,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.196138688828796,
"count": 18208,
"is_parallel": true,
"self": 2.196138688828796
},
"communicator.exchange": {
"total": 67.31191313015006,
"count": 18208,
"is_parallel": true,
"self": 67.31191313015006
},
"steps_from_proto": {
"total": 12.407672586617991,
"count": 18208,
"is_parallel": true,
"self": 2.4541078687179834,
"children": {
"_process_rank_one_or_two_observation": {
"total": 9.953564717900008,
"count": 182080,
"is_parallel": true,
"self": 9.953564717900008
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.88599975546822e-05,
"count": 1,
"self": 6.88599975546822e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 181.3120569051389,
"count": 129760,
"is_parallel": true,
"self": 1.0343860988214146,
"children": {
"process_trajectory": {
"total": 96.94700801130966,
"count": 129760,
"is_parallel": true,
"self": 96.50593304431823,
"children": {
"RLTrainer._checkpoint": {
"total": 0.44107496699143667,
"count": 4,
"is_parallel": true,
"self": 0.44107496699143667
}
}
},
"_update_policy": {
"total": 83.33066279500781,
"count": 90,
"is_parallel": true,
"self": 25.919892322315718,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.41077047269209,
"count": 4587,
"is_parallel": true,
"self": 57.41077047269209
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0741367349983193,
"count": 1,
"self": 0.0007672310021007434,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07336950399621855,
"count": 1,
"self": 0.07336950399621855
}
}
}
}
}
}
}