|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SnowballTarget.Policy.Entropy.mean": { |
|
"value": 1.0002515316009521, |
|
"min": 0.9846835136413574, |
|
"max": 2.8746535778045654, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Entropy.sum": { |
|
"value": 9550.4013671875, |
|
"min": 9488.41015625, |
|
"max": 29439.328125, |
|
"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": 12.839152336120605, |
|
"min": 0.3226393163204193, |
|
"max": 12.839152336120605, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 2503.634765625, |
|
"min": 62.59202575683594, |
|
"max": 2611.6923828125, |
|
"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": 0.0665206545453853, |
|
"min": 0.06066817989317226, |
|
"max": 0.0727261286839505, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.sum": { |
|
"value": 0.2660826181815412, |
|
"min": 0.24267271957268904, |
|
"max": 0.3590564107422217, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.mean": { |
|
"value": 0.19482998736202717, |
|
"min": 0.10282149994928463, |
|
"max": 0.2729565479007422, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.sum": { |
|
"value": 0.7793199494481087, |
|
"min": 0.41128599979713854, |
|
"max": 1.3647827395037109, |
|
"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": 25.227272727272727, |
|
"min": 2.75, |
|
"max": 25.490909090909092, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.sum": { |
|
"value": 1110.0, |
|
"min": 121.0, |
|
"max": 1402.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.mean": { |
|
"value": 25.227272727272727, |
|
"min": 2.75, |
|
"max": 25.490909090909092, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.sum": { |
|
"value": 1110.0, |
|
"min": 121.0, |
|
"max": 1402.0, |
|
"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": "1724100586", |
|
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", |
|
"numpy_version": "1.23.5", |
|
"end_time_seconds": "1724101027" |
|
}, |
|
"total": 440.78805245499996, |
|
"count": 1, |
|
"self": 0.44046633599998586, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.06035034300009556, |
|
"count": 1, |
|
"self": 0.06035034300009556 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 440.2872357759999, |
|
"count": 1, |
|
"self": 0.5538074030316693, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 2.851688809999928, |
|
"count": 1, |
|
"self": 2.851688809999928 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 436.7876249899682, |
|
"count": 18200, |
|
"self": 0.25833976695673755, |
|
"children": { |
|
"env_step": { |
|
"total": 436.52928522301147, |
|
"count": 18200, |
|
"self": 283.28876279502197, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 152.97221014399975, |
|
"count": 18200, |
|
"self": 1.41220352700509, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 151.56000661699466, |
|
"count": 18200, |
|
"self": 151.56000661699466 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.2683122839897578, |
|
"count": 18200, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 439.12969405399167, |
|
"count": 18200, |
|
"is_parallel": true, |
|
"self": 223.95802136100053, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005894438999916929, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.003869217999749708, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.002025221000167221, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.002025221000167221 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.03503848800005471, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006511130000035337, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00040581300004305376, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00040581300004305376 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.03203605900000639, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.03203605900000639 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001945503000001736, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00035709100018266327, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0015884119998190727, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0015884119998190727 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 215.17167269299114, |
|
"count": 18199, |
|
"is_parallel": true, |
|
"self": 9.806718906002516, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 5.051642786980892, |
|
"count": 18199, |
|
"is_parallel": true, |
|
"self": 5.051642786980892 |
|
}, |
|
"communicator.exchange": { |
|
"total": 168.07127943900787, |
|
"count": 18199, |
|
"is_parallel": true, |
|
"self": 168.07127943900787 |
|
}, |
|
"steps_from_proto": { |
|
"total": 32.24203156099986, |
|
"count": 18199, |
|
"is_parallel": true, |
|
"self": 6.049299813998346, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 26.192731747001517, |
|
"count": 181990, |
|
"is_parallel": true, |
|
"self": 26.192731747001517 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 0.00016722999998819432, |
|
"count": 1, |
|
"self": 0.00016722999998819432, |
|
"children": { |
|
"thread_root": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"trainer_advance": { |
|
"total": 431.6704795371354, |
|
"count": 649989, |
|
"is_parallel": true, |
|
"self": 13.3077665250579, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 236.9679674050791, |
|
"count": 649989, |
|
"is_parallel": true, |
|
"self": 236.3227182610791, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.6452491439999903, |
|
"count": 4, |
|
"is_parallel": true, |
|
"self": 0.6452491439999903 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 181.3947456069984, |
|
"count": 90, |
|
"is_parallel": true, |
|
"self": 58.49011651200669, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 122.90462909499172, |
|
"count": 4587, |
|
"is_parallel": true, |
|
"self": 122.90462909499172 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09394734300008167, |
|
"count": 1, |
|
"self": 0.0009380880001117475, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09300925499996993, |
|
"count": 1, |
|
"self": 0.09300925499996993 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |