{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.996234118938446, "min": 0.996234118938446, "max": 2.8609232902526855, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9523.001953125, "min": 9523.001953125, "max": 29424.595703125, "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": 12.770721435546875, "min": 0.41473981738090515, "max": 12.770721435546875, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2490.290771484375, "min": 80.45952606201172, "max": 2589.152099609375, "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": 0.072603259838241, "min": 0.06265202038561897, "max": 0.072603259838241, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.290413039352964, "min": 0.2506080815424759, "max": 0.3511773361493468, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19110269986969583, "min": 0.12294448377603355, "max": 0.276744973937086, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7644107994787833, "min": 0.4917779351041342, "max": 1.313646506152901, "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": 25.022727272727273, "min": 3.409090909090909, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1101.0, "min": 150.0, "max": 1373.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.022727272727273, "min": 3.409090909090909, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1101.0, "min": 150.0, "max": 1373.0, "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": "1710376605", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710377165" }, "total": 559.465408193, "count": 1, "self": 0.5910561510000889, "children": { "run_training.setup": { "total": 0.0660753490000161, "count": 1, "self": 0.0660753490000161 }, "TrainerController.start_learning": { "total": 558.8082766929999, "count": 1, "self": 0.7464833830013049, "children": { "TrainerController._reset_env": { "total": 2.714552308000009, "count": 1, "self": 2.714552308000009 }, "TrainerController.advance": { "total": 555.2566410499985, "count": 18200, "self": 0.39029827899378233, "children": { "env_step": { "total": 554.8663427710047, "count": 18200, "self": 423.98648444801285, "children": { "SubprocessEnvManager._take_step": { "total": 130.47397437399377, "count": 18200, "self": 1.9674803560006922, "children": { "TorchPolicy.evaluate": { "total": 128.50649401799308, "count": 18200, "self": 128.50649401799308 } } }, "workers": { "total": 0.40588394899810964, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 557.161356198996, "count": 18200, "is_parallel": true, "self": 261.2292240339889, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0053854849999765975, "count": 1, "is_parallel": true, "self": 0.0036457309998922938, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017397540000843037, "count": 10, "is_parallel": true, "self": 0.0017397540000843037 } } }, "UnityEnvironment.step": { "total": 0.08455821799998375, "count": 1, "is_parallel": true, "self": 0.0008010859999671993, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004488010000045506, "count": 1, "is_parallel": true, "self": 0.0004488010000045506 }, "communicator.exchange": { "total": 0.08104354300002115, "count": 1, "is_parallel": true, "self": 0.08104354300002115 }, "steps_from_proto": { "total": 0.0022647879999908582, "count": 1, "is_parallel": true, "self": 0.0004749020000645032, "children": { "_process_rank_one_or_two_observation": { "total": 0.001789885999926355, "count": 10, "is_parallel": true, "self": 0.001789885999926355 } } } } } } }, "UnityEnvironment.step": { "total": 295.93213216500715, "count": 18199, "is_parallel": true, "self": 13.756282364990852, "children": { "UnityEnvironment._generate_step_input": { "total": 7.2879569120049155, "count": 18199, "is_parallel": true, "self": 7.2879569120049155 }, "communicator.exchange": { "total": 231.84738200401006, "count": 18199, "is_parallel": true, "self": 231.84738200401006 }, "steps_from_proto": { "total": 43.04051088400132, "count": 18199, "is_parallel": true, "self": 8.597457861002852, "children": { "_process_rank_one_or_two_observation": { "total": 34.44305302299847, "count": 181990, "is_parallel": true, "self": 34.44305302299847 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013777000003756257, "count": 1, "self": 0.00013777000003756257, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 548.659088590035, "count": 756400, "is_parallel": true, "self": 17.48859956500587, "children": { "process_trajectory": { "total": 297.2414988820291, "count": 756400, "is_parallel": true, "self": 296.35109240202894, "children": { "RLTrainer._checkpoint": { "total": 0.8904064800001379, "count": 4, "is_parallel": true, "self": 0.8904064800001379 } } }, "_update_policy": { "total": 233.92899014300002, "count": 90, "is_parallel": true, "self": 61.49349237799953, "children": { "TorchPPOOptimizer.update": { "total": 172.4354977650005, "count": 4587, "is_parallel": true, "self": 172.4354977650005 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09046218200001022, "count": 1, "self": 0.0011874580000039714, "children": { "RLTrainer._checkpoint": { "total": 0.08927472400000624, "count": 1, "self": 0.08927472400000624 } } } } } } }