{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7683303952217102, "min": 0.7530207633972168, "max": 2.8647408485412598, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7352.921875, "min": 7352.921875, "max": 29369.32421875, "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": 12.84871768951416, "min": 0.32490670680999756, "max": 12.84871768951416, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2505.5, "min": 63.031898498535156, "max": 2612.135009765625, "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": 0.0746033734276174, "min": 0.06134941078249967, "max": 0.07645600064949808, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2984134937104696, "min": 0.24821274587428016, "max": 0.3822800032474904, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17907044035839098, "min": 0.1369045376480904, "max": 0.26973822801282593, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7162817614335639, "min": 0.5476181505923616, "max": 1.3486911400641297, "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": 25.454545454545453, "min": 3.2954545454545454, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 145.0, "max": 1380.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.2954545454545454, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 145.0, "max": 1380.0, "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": "1730359557", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1730360188" }, "total": 631.534588147, "count": 1, "self": 0.5790236600000753, "children": { "run_training.setup": { "total": 0.07225663799999893, "count": 1, "self": 0.07225663799999893 }, "TrainerController.start_learning": { "total": 630.883307849, "count": 1, "self": 0.8952701419937057, "children": { "TrainerController._reset_env": { "total": 7.676810880999994, "count": 1, "self": 7.676810880999994 }, "TrainerController.advance": { "total": 622.2211391730062, "count": 18202, "self": 0.4424266670076804, "children": { "env_step": { "total": 621.7787125059986, "count": 18202, "self": 476.5983830809963, "children": { "SubprocessEnvManager._take_step": { "total": 144.76118961300125, "count": 18202, "self": 2.736611968004155, "children": { "TorchPolicy.evaluate": { "total": 142.0245776449971, "count": 18202, "self": 142.0245776449971 } } }, "workers": { "total": 0.41913981200099215, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 628.9468008720008, "count": 18202, "is_parallel": true, "self": 304.6513295480079, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003229352999994717, "count": 1, "is_parallel": true, "self": 0.0007784349999724327, "children": { "_process_rank_one_or_two_observation": { "total": 0.002450918000022284, "count": 10, "is_parallel": true, "self": 0.002450918000022284 } } }, "UnityEnvironment.step": { "total": 0.04407740199999921, "count": 1, "is_parallel": true, "self": 0.0009119810000015605, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005519449999837889, "count": 1, "is_parallel": true, "self": 0.0005519449999837889 }, "communicator.exchange": { "total": 0.04022521300001358, "count": 1, "is_parallel": true, "self": 0.04022521300001358 }, "steps_from_proto": { "total": 0.002388263000000279, "count": 1, "is_parallel": true, "self": 0.0004654050000567622, "children": { "_process_rank_one_or_two_observation": { "total": 0.001922857999943517, "count": 10, "is_parallel": true, "self": 0.001922857999943517 } } } } } } }, "UnityEnvironment.step": { "total": 324.29547132399296, "count": 18201, "is_parallel": true, "self": 15.255984125986402, "children": { "UnityEnvironment._generate_step_input": { "total": 7.690999937007859, "count": 18201, "is_parallel": true, "self": 7.690999937007859 }, "communicator.exchange": { "total": 256.33841463699366, "count": 18201, "is_parallel": true, "self": 256.33841463699366 }, "steps_from_proto": { "total": 45.01007262400506, "count": 18201, "is_parallel": true, "self": 9.187126693989086, "children": { "_process_rank_one_or_two_observation": { "total": 35.822945930015976, "count": 182010, "is_parallel": true, "self": 35.822945930015976 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0005601979999028117, "count": 1, "self": 0.0005601979999028117, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 615.360295440019, "count": 740118, "is_parallel": true, "self": 18.116923506029707, "children": { "process_trajectory": { "total": 327.9235319659892, "count": 740118, "is_parallel": true, "self": 326.82802402398926, "children": { "RLTrainer._checkpoint": { "total": 1.0955079419999265, "count": 4, "is_parallel": true, "self": 1.0955079419999265 } } }, "_update_policy": { "total": 269.3198399680001, "count": 90, "is_parallel": true, "self": 76.59948734500031, "children": { "TorchPPOOptimizer.update": { "total": 192.7203526229998, "count": 4584, "is_parallel": true, "self": 192.7203526229998 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08952745500005221, "count": 1, "self": 0.0012337570001363929, "children": { "RLTrainer._checkpoint": { "total": 0.08829369799991582, "count": 1, "self": 0.08829369799991582 } } } } } } }