{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9020704030990601, "min": 0.9020704030990601, "max": 2.857469320297241, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8573.27734375, "min": 8573.27734375, "max": 29169.046875, "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": 13.027749061584473, "min": 0.403626024723053, "max": 13.027749061584473, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2540.4111328125, "min": 78.30345153808594, "max": 2634.771484375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07092409486344253, "min": 0.06210016383008813, "max": 0.07358351097112367, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28369637945377013, "min": 0.2553726443441644, "max": 0.36248345753661926, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2039130240970967, "min": 0.11594586364705772, "max": 0.27624960769625273, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8156520963883868, "min": 0.4637834545882309, "max": 1.3812480384812635, "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.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.Environment.CumulativeReward.mean": { "value": 25.227272727272727, "min": 3.409090909090909, "max": 26.181818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1110.0, "min": 150.0, "max": 1440.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.227272727272727, "min": 3.409090909090909, "max": 26.181818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1110.0, "min": 150.0, "max": 1440.0, "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": "1751578089", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1751578514" }, "total": 424.6787678989999, "count": 1, "self": 0.43898006999995687, "children": { "run_training.setup": { "total": 0.027765059999978803, "count": 1, "self": 0.027765059999978803 }, "TrainerController.start_learning": { "total": 424.212022769, "count": 1, "self": 0.34400337799422687, "children": { "TrainerController._reset_env": { "total": 3.3302995600000713, "count": 1, "self": 3.3302995600000713 }, "TrainerController.advance": { "total": 420.4529301500057, "count": 18192, "self": 0.3772603550060012, "children": { "env_step": { "total": 302.4196614550033, "count": 18192, "self": 232.9071070709931, "children": { "SubprocessEnvManager._take_step": { "total": 69.30615057100158, "count": 18192, "self": 1.2391972900052224, "children": { "TorchPolicy.evaluate": { "total": 68.06695328099636, "count": 18192, "self": 68.06695328099636 } } }, "workers": { "total": 0.2064038130085919, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 422.7985918379974, "count": 18192, "is_parallel": true, "self": 218.25501189800798, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007569951999926161, "count": 1, "is_parallel": true, "self": 0.005501998000227104, "children": { "_process_rank_one_or_two_observation": { "total": 0.002067953999699057, "count": 10, "is_parallel": true, "self": 0.002067953999699057 } } }, "UnityEnvironment.step": { "total": 0.03877187699993101, "count": 1, "is_parallel": true, "self": 0.0006031289998418288, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000428679000037846, "count": 1, "is_parallel": true, "self": 0.000428679000037846 }, "communicator.exchange": { "total": 0.035802943000021514, "count": 1, "is_parallel": true, "self": 0.035802943000021514 }, "steps_from_proto": { "total": 0.0019371260000298207, "count": 1, "is_parallel": true, "self": 0.00040312699979949684, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015339990002303239, "count": 10, "is_parallel": true, "self": 0.0015339990002303239 } } } } } } }, "UnityEnvironment.step": { "total": 204.5435799399894, "count": 18191, "is_parallel": true, "self": 9.731381258985607, "children": { "UnityEnvironment._generate_step_input": { "total": 5.421771626006944, "count": 18191, "is_parallel": true, "self": 5.421771626006944 }, "communicator.exchange": { "total": 157.62427779499944, "count": 18191, "is_parallel": true, "self": 157.62427779499944 }, "steps_from_proto": { "total": 31.766149259997405, "count": 18191, "is_parallel": true, "self": 5.573857854993662, "children": { "_process_rank_one_or_two_observation": { "total": 26.192291405003743, "count": 181910, "is_parallel": true, "self": 26.192291405003743 } } } } } } } } } } }, "trainer_advance": { "total": 117.65600833999645, "count": 18192, "self": 0.41780292499140614, "children": { "process_trajectory": { "total": 26.047330495004303, "count": 18192, "self": 25.659875659004115, "children": { "RLTrainer._checkpoint": { "total": 0.38745483600018815, "count": 4, "self": 0.38745483600018815 } } }, "_update_policy": { "total": 91.19087492000074, "count": 90, "self": 38.11585444600132, "children": { "TorchPPOOptimizer.update": { "total": 53.075020473999416, "count": 4587, "self": 53.075020473999416 } } } } } } }, "trainer_threads": { "total": 1.204999989568023e-06, "count": 1, "self": 1.204999989568023e-06 }, "TrainerController._save_models": { "total": 0.08478847599997152, "count": 1, "self": 0.0008531109999694308, "children": { "RLTrainer._checkpoint": { "total": 0.0839353650000021, "count": 1, "self": 0.0839353650000021 } } } } } } }