|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SnowballTarget.Policy.Entropy.mean": { |
|
"value": 0.9148550629615784, |
|
"min": 0.9148550629615784, |
|
"max": 2.871063709259033, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Entropy.sum": { |
|
"value": 8775.2900390625, |
|
"min": 8775.2900390625, |
|
"max": 29592.052734375, |
|
"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": 13.279151916503906, |
|
"min": 0.3671874701976776, |
|
"max": 13.279151916503906, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 2589.4345703125, |
|
"min": 71.23436737060547, |
|
"max": 2705.75341796875, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.CuriosityValueEstimate.mean": { |
|
"value": 0.09546870738267899, |
|
"min": -0.016660604625940323, |
|
"max": 0.14152777194976807, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.CuriosityValueEstimate.sum": { |
|
"value": 18.616397857666016, |
|
"min": -3.2321572303771973, |
|
"max": 28.998111724853516, |
|
"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": 0.06405558330623214, |
|
"min": 0.06131177520457605, |
|
"max": 0.07274797403906454, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.sum": { |
|
"value": 0.25622233322492854, |
|
"min": 0.2452471008183042, |
|
"max": 0.3578633572468985, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.mean": { |
|
"value": 0.09076593071222307, |
|
"min": 0.06346269041886463, |
|
"max": 0.14713705880384823, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.sum": { |
|
"value": 0.36306372284889227, |
|
"min": 0.2538507616754585, |
|
"max": 0.7356852940192411, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.LearningRate.mean": { |
|
"value": 1.347009730600001e-05, |
|
"min": 1.347009730600001e-05, |
|
"max": 0.00048647000270600005, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.LearningRate.sum": { |
|
"value": 5.388038922400004e-05, |
|
"min": 5.388038922400004e-05, |
|
"max": 0.00230860003828, |
|
"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.Losses.CuriosityForwardLoss.mean": { |
|
"value": 0.048958304703381715, |
|
"min": 0.04579419151459839, |
|
"max": 0.15781561710743924, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.CuriosityForwardLoss.sum": { |
|
"value": 0.19583321881352686, |
|
"min": 0.18317676605839356, |
|
"max": 0.631262468429757, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.CuriosityInverseLoss.mean": { |
|
"value": 0.7864058046948676, |
|
"min": 0.7864058046948676, |
|
"max": 2.746093947440386, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.CuriosityInverseLoss.sum": { |
|
"value": 3.1456232187794706, |
|
"min": 3.1456232187794706, |
|
"max": 12.928630973778517, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.mean": { |
|
"value": 26.204545454545453, |
|
"min": 3.5681818181818183, |
|
"max": 26.227272727272727, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.sum": { |
|
"value": 1153.0, |
|
"min": 157.0, |
|
"max": 1437.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.mean": { |
|
"value": 26.204545454545453, |
|
"min": 3.5681818181818183, |
|
"max": 26.227272727272727, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.sum": { |
|
"value": 1153.0, |
|
"min": 157.0, |
|
"max": 1437.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.CuriosityReward.mean": { |
|
"value": 0.20874647542156957, |
|
"min": 0.18558931982737373, |
|
"max": 0.3610852147791196, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.CuriosityReward.sum": { |
|
"value": 9.18484491854906, |
|
"min": 8.369245985755697, |
|
"max": 18.326926595065743, |
|
"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": "1679309527", |
|
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --force --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", |
|
"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": "1679310023" |
|
}, |
|
"total": 496.126232927, |
|
"count": 1, |
|
"self": 0.4321505809999735, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10164176199998565, |
|
"count": 1, |
|
"self": 0.10164176199998565 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 495.59244058400003, |
|
"count": 1, |
|
"self": 0.5057200699996542, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 5.669090515999983, |
|
"count": 1, |
|
"self": 5.669090515999983 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 489.27926407600035, |
|
"count": 18207, |
|
"self": 0.26358151098952476, |
|
"children": { |
|
"env_step": { |
|
"total": 489.0156825650108, |
|
"count": 18207, |
|
"self": 374.3602393810067, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 114.40971856100134, |
|
"count": 18207, |
|
"self": 2.4003941179956314, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 112.00932444300571, |
|
"count": 18207, |
|
"self": 112.00932444300571 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.2457246230027863, |
|
"count": 18207, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 494.29986508100575, |
|
"count": 18207, |
|
"is_parallel": true, |
|
"self": 261.6230163290066, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.002236798000012641, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000609027999985301, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0016277700000273398, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0016277700000273398 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.036456725999983064, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00034808499987093455, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00038980500005436625, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00038980500005436625 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.034627486000033514, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.034627486000033514 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0010913500000242493, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00023414499992213678, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0008572050001021125, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0008572050001021125 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 232.67684875199916, |
|
"count": 18206, |
|
"is_parallel": true, |
|
"self": 9.171589949998577, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 5.068321562999074, |
|
"count": 18206, |
|
"is_parallel": true, |
|
"self": 5.068321562999074 |
|
}, |
|
"communicator.exchange": { |
|
"total": 188.43024679299663, |
|
"count": 18206, |
|
"is_parallel": true, |
|
"self": 188.43024679299663 |
|
}, |
|
"steps_from_proto": { |
|
"total": 30.006690446004882, |
|
"count": 18206, |
|
"is_parallel": true, |
|
"self": 5.899886635006624, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 24.106803810998258, |
|
"count": 182060, |
|
"is_parallel": true, |
|
"self": 24.106803810998258 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 0.00011686300001656491, |
|
"count": 1, |
|
"self": 0.00011686300001656491, |
|
"children": { |
|
"thread_root": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"trainer_advance": { |
|
"total": 486.4422729110031, |
|
"count": 354380, |
|
"is_parallel": true, |
|
"self": 8.490131191010732, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 253.2704820709924, |
|
"count": 354380, |
|
"is_parallel": true, |
|
"self": 252.10741830299247, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 1.1630637679999154, |
|
"count": 4, |
|
"is_parallel": true, |
|
"self": 1.1630637679999154 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 224.68165964899998, |
|
"count": 90, |
|
"is_parallel": true, |
|
"self": 138.39125454399885, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 86.29040510500113, |
|
"count": 4584, |
|
"is_parallel": true, |
|
"self": 86.29040510500113 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.1382490590000316, |
|
"count": 1, |
|
"self": 0.0010270330000139438, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.13722202600001765, |
|
"count": 1, |
|
"self": 0.13722202600001765 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |