|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SnowballTarget.Policy.Entropy.mean": { |
|
"value": 1.1544607877731323, |
|
"min": 1.1418404579162598, |
|
"max": 2.8374648094177246, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Entropy.sum": { |
|
"value": 11022.7919921875, |
|
"min": 10487.26953125, |
|
"max": 28358.654296875, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Step.mean": { |
|
"value": 199960.0, |
|
"min": 9992.0, |
|
"max": 199960.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Step.sum": { |
|
"value": 199960.0, |
|
"min": 9992.0, |
|
"max": 199960.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 12.51748275756836, |
|
"min": 0.5854502320289612, |
|
"max": 12.51748275756836, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 2440.9091796875, |
|
"min": 37.468814849853516, |
|
"max": 2501.917724609375, |
|
"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": 2189.0, |
|
"max": 10945.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.mean": { |
|
"value": 0.07200062442394019, |
|
"min": 0.06332857517723003, |
|
"max": 0.07463651072248467, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.sum": { |
|
"value": 0.28800249769576075, |
|
"min": 0.07463651072248467, |
|
"max": 0.3631651440073791, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.mean": { |
|
"value": 0.20859267577236773, |
|
"min": 0.12093222917368014, |
|
"max": 0.2943200986759335, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.sum": { |
|
"value": 0.8343707030894709, |
|
"min": 0.12093222917368014, |
|
"max": 1.4716004933796676, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.LearningRate.mean": { |
|
"value": 8.214097262000005e-06, |
|
"min": 8.214097262000005e-06, |
|
"max": 0.000287064004312, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.LearningRate.sum": { |
|
"value": 3.285638904800002e-05, |
|
"min": 3.285638904800002e-05, |
|
"max": 0.0013858200380599999, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Epsilon.mean": { |
|
"value": 0.10273800000000001, |
|
"min": 0.10273800000000001, |
|
"max": 0.195688, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Epsilon.sum": { |
|
"value": 0.41095200000000004, |
|
"min": 0.195688, |
|
"max": 0.96194, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Beta.mean": { |
|
"value": 0.0001466262000000001, |
|
"min": 0.0001466262000000001, |
|
"max": 0.0047848312, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Beta.sum": { |
|
"value": 0.0005865048000000004, |
|
"min": 0.0005865048000000004, |
|
"max": 0.023100806, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.mean": { |
|
"value": 25.181818181818183, |
|
"min": 3.0, |
|
"max": 25.181818181818183, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.sum": { |
|
"value": 1108.0, |
|
"min": 33.0, |
|
"max": 1356.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.mean": { |
|
"value": 25.181818181818183, |
|
"min": 3.0, |
|
"max": 25.181818181818183, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.sum": { |
|
"value": 1108.0, |
|
"min": 33.0, |
|
"max": 1356.0, |
|
"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": "1676357815", |
|
"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 --resume", |
|
"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": "1676358244" |
|
}, |
|
"total": 429.195851535, |
|
"count": 1, |
|
"self": 0.7867629780000698, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10947037599999021, |
|
"count": 1, |
|
"self": 0.10947037599999021 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 428.2996181809999, |
|
"count": 1, |
|
"self": 0.4835444070047288, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 7.101543563000064, |
|
"count": 1, |
|
"self": 7.101543563000064 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 420.54435335099504, |
|
"count": 17601, |
|
"self": 0.2362031210132045, |
|
"children": { |
|
"env_step": { |
|
"total": 420.30815022998183, |
|
"count": 17601, |
|
"self": 287.01985280700194, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 133.04257722399723, |
|
"count": 17601, |
|
"self": 1.337058558982335, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 131.7055186650149, |
|
"count": 17601, |
|
"self": 28.767387893044088, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 102.9381307719708, |
|
"count": 17601, |
|
"self": 102.9381307719708 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.24572019898266717, |
|
"count": 17601, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 426.8952240950083, |
|
"count": 17601, |
|
"is_parallel": true, |
|
"self": 204.91237196101076, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.002771187000007558, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0009383529999240636, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0018328340000834942, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0018328340000834942 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.048828276999984155, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00035553700013224443, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.000303159999930358, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000303159999930358 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.046980107999957, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.046980107999957 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001189471999964553, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00031896499990580196, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0008705070000587511, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0008705070000587511 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 221.98285213399754, |
|
"count": 17600, |
|
"is_parallel": true, |
|
"self": 8.80142734503238, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 4.804668293981649, |
|
"count": 17600, |
|
"is_parallel": true, |
|
"self": 4.804668293981649 |
|
}, |
|
"communicator.exchange": { |
|
"total": 177.39940563599407, |
|
"count": 17600, |
|
"is_parallel": true, |
|
"self": 177.39940563599407 |
|
}, |
|
"steps_from_proto": { |
|
"total": 30.97735085898944, |
|
"count": 17600, |
|
"is_parallel": true, |
|
"self": 6.243455937015938, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 24.7338949219735, |
|
"count": 176000, |
|
"is_parallel": true, |
|
"self": 24.7338949219735 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 0.00010480700007065025, |
|
"count": 1, |
|
"self": 0.00010480700007065025, |
|
"children": { |
|
"thread_root": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"trainer_advance": { |
|
"total": 417.3458928389284, |
|
"count": 376609, |
|
"is_parallel": true, |
|
"self": 9.302657343984947, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 241.24910940894392, |
|
"count": 376609, |
|
"is_parallel": true, |
|
"self": 239.79841103594413, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 1.4506983729997955, |
|
"count": 4, |
|
"is_parallel": true, |
|
"self": 1.4506983729997955 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 166.79412608599955, |
|
"count": 87, |
|
"is_parallel": true, |
|
"self": 55.87059514500356, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 110.92353094099599, |
|
"count": 4434, |
|
"is_parallel": true, |
|
"self": 110.92353094099599 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.1700720530000126, |
|
"count": 1, |
|
"self": 0.002315073000090706, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1677569799999219, |
|
"count": 1, |
|
"self": 0.1677569799999219 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |