|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SnowballTarget.Policy.Entropy.mean": { |
|
"value": 1.0914065837860107, |
|
"min": 1.0840957164764404, |
|
"max": 2.849740505218506, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Entropy.sum": { |
|
"value": 10420.75, |
|
"min": 10420.75, |
|
"max": 29184.19140625, |
|
"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": 12.292169570922852, |
|
"min": 0.3689696788787842, |
|
"max": 12.292169570922852, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 2396.97314453125, |
|
"min": 71.58011627197266, |
|
"max": 2463.79638671875, |
|
"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": 0.06838773853229999, |
|
"min": 0.06472914174148316, |
|
"max": 0.07313575454644723, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.sum": { |
|
"value": 0.27355095412919994, |
|
"min": 0.25983983494099416, |
|
"max": 0.35337813594635326, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.mean": { |
|
"value": 0.2335727519410498, |
|
"min": 0.12455451609247237, |
|
"max": 0.2790822603685015, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.sum": { |
|
"value": 0.9342910077641992, |
|
"min": 0.49821806436988947, |
|
"max": 1.3816593815298641, |
|
"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": 24.40909090909091, |
|
"min": 3.3636363636363638, |
|
"max": 24.40909090909091, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.sum": { |
|
"value": 1074.0, |
|
"min": 148.0, |
|
"max": 1341.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.mean": { |
|
"value": 24.40909090909091, |
|
"min": 3.3636363636363638, |
|
"max": 24.40909090909091, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.sum": { |
|
"value": 1074.0, |
|
"min": 148.0, |
|
"max": 1341.0, |
|
"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": "1675187537", |
|
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", |
|
"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": "0.29.0.dev0", |
|
"mlagents_envs_version": "0.29.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.8.1+cu102", |
|
"numpy_version": "1.21.6", |
|
"end_time_seconds": "1675187982" |
|
}, |
|
"total": 444.97213678700007, |
|
"count": 1, |
|
"self": 0.3825589910001099, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11469908699996267, |
|
"count": 1, |
|
"self": 0.11469908699996267 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 444.474878709, |
|
"count": 1, |
|
"self": 0.5314036310128358, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 10.24903120099998, |
|
"count": 1, |
|
"self": 10.24903120099998 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 433.5752843739874, |
|
"count": 18201, |
|
"self": 0.29663476699477087, |
|
"children": { |
|
"env_step": { |
|
"total": 433.27864960699264, |
|
"count": 18201, |
|
"self": 282.01113363798663, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 150.99114228702217, |
|
"count": 18201, |
|
"self": 1.425668758025381, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 149.5654735289968, |
|
"count": 18201, |
|
"self": 34.134251230980794, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 115.431222298016, |
|
"count": 18201, |
|
"self": 115.431222298016 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.2763736819838414, |
|
"count": 18201, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 443.13609605499835, |
|
"count": 18201, |
|
"is_parallel": true, |
|
"self": 215.08938043699652, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.006256388999986484, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.003494819000025018, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0027615699999614662, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0027615699999614662 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04363007500001004, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005288309999968988, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0003953589999809992, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003953589999809992 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04080427300004885, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04080427300004885 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0019016119999832881, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004753470001332971, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001426264999849991, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.001426264999849991 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 228.04671561800183, |
|
"count": 18200, |
|
"is_parallel": true, |
|
"self": 8.516585480971685, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 5.154122930012704, |
|
"count": 18200, |
|
"is_parallel": true, |
|
"self": 5.154122930012704 |
|
}, |
|
"communicator.exchange": { |
|
"total": 182.88006028200323, |
|
"count": 18200, |
|
"is_parallel": true, |
|
"self": 182.88006028200323 |
|
}, |
|
"steps_from_proto": { |
|
"total": 31.49594692501421, |
|
"count": 18200, |
|
"is_parallel": true, |
|
"self": 6.778943787966455, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 24.717003137047755, |
|
"count": 182000, |
|
"is_parallel": true, |
|
"self": 24.717003137047755 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 4.4789999947170145e-05, |
|
"count": 1, |
|
"self": 4.4789999947170145e-05, |
|
"children": { |
|
"thread_root": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"trainer_advance": { |
|
"total": 430.5141334929805, |
|
"count": 350647, |
|
"is_parallel": true, |
|
"self": 9.701014956932681, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 247.62444607604846, |
|
"count": 350647, |
|
"is_parallel": true, |
|
"self": 246.80741950204833, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.8170265740001241, |
|
"count": 4, |
|
"is_parallel": true, |
|
"self": 0.8170265740001241 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 173.18867245999934, |
|
"count": 90, |
|
"is_parallel": true, |
|
"self": 43.11652540999478, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 130.07214705000456, |
|
"count": 4587, |
|
"is_parallel": true, |
|
"self": 130.07214705000456 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.11911471299981713, |
|
"count": 1, |
|
"self": 0.0009041489997798635, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.11821056400003727, |
|
"count": 1, |
|
"self": 0.11821056400003727 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |