{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.973695695400238, "min": 0.973695695400238, "max": 2.8549792766571045, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9254.00390625, "min": 9254.00390625, "max": 29143.62890625, "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": 12.256503105163574, "min": 0.4036545157432556, "max": 12.256503105163574, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2390.01806640625, "min": 78.30897521972656, "max": 2495.692626953125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07158147561587576, "min": 0.06273912080334197, "max": 0.0744391910425917, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28632590246350303, "min": 0.26677164336833104, "max": 0.36838737001566113, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20678835077320828, "min": 0.1311304628958597, "max": 0.2832913887413109, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8271534030928331, "min": 0.5245218515834388, "max": 1.4031612192298852, "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": 24.477272727272727, "min": 3.909090909090909, "max": 24.477272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1077.0, "min": 172.0, "max": 1322.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.477272727272727, "min": 3.909090909090909, "max": 24.477272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1077.0, "min": 172.0, "max": 1322.0, "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": "1743088671", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1743089123" }, "total": 452.554158638, "count": 1, "self": 0.441208720999839, "children": { "run_training.setup": { "total": 0.023357152000016868, "count": 1, "self": 0.023357152000016868 }, "TrainerController.start_learning": { "total": 452.08959276500013, "count": 1, "self": 0.4166127389898975, "children": { "TrainerController._reset_env": { "total": 3.0234254489998875, "count": 1, "self": 3.0234254489998875 }, "TrainerController.advance": { "total": 448.5509439870102, "count": 18192, "self": 0.41422481900804087, "children": { "env_step": { "total": 322.88827720700806, "count": 18192, "self": 245.67673477700282, "children": { "SubprocessEnvManager._take_step": { "total": 76.96581900600768, "count": 18192, "self": 1.3596524469928681, "children": { "TorchPolicy.evaluate": { "total": 75.60616655901481, "count": 18192, "self": 75.60616655901481 } } }, "workers": { "total": 0.24572342399756053, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 450.362758076001, "count": 18192, "is_parallel": true, "self": 235.30824013700067, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005429712000022846, "count": 1, "is_parallel": true, "self": 0.0038433279999026126, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015863840001202334, "count": 10, "is_parallel": true, "self": 0.0015863840001202334 } } }, "UnityEnvironment.step": { "total": 0.03808514699994703, "count": 1, "is_parallel": true, "self": 0.0005905380000967853, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039637299983041885, "count": 1, "is_parallel": true, "self": 0.00039637299983041885 }, "communicator.exchange": { "total": 0.0350762069999746, "count": 1, "is_parallel": true, "self": 0.0350762069999746 }, "steps_from_proto": { "total": 0.0020220290000452223, "count": 1, "is_parallel": true, "self": 0.00038537399973392894, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016366550003112934, "count": 10, "is_parallel": true, "self": 0.0016366550003112934 } } } } } } }, "UnityEnvironment.step": { "total": 215.05451793900033, "count": 18191, "is_parallel": true, "self": 10.122878650988923, "children": { "UnityEnvironment._generate_step_input": { "total": 5.8023950460078595, "count": 18191, "is_parallel": true, "self": 5.8023950460078595 }, "communicator.exchange": { "total": 165.47236455898837, "count": 18191, "is_parallel": true, "self": 165.47236455898837 }, "steps_from_proto": { "total": 33.65687968301518, "count": 18191, "is_parallel": true, "self": 6.194681556000887, "children": { "_process_rank_one_or_two_observation": { "total": 27.46219812701429, "count": 181910, "is_parallel": true, "self": 27.46219812701429 } } } } } } } } } } }, "trainer_advance": { "total": 125.24844196099411, "count": 18192, "self": 0.533658574996025, "children": { "process_trajectory": { "total": 27.952191768997864, "count": 18192, "self": 27.351038747998018, "children": { "RLTrainer._checkpoint": { "total": 0.6011530209998455, "count": 4, "self": 0.6011530209998455 } } }, "_update_policy": { "total": 96.76259161700023, "count": 90, "self": 38.9345906079966, "children": { "TorchPPOOptimizer.update": { "total": 57.82800100900363, "count": 4587, "self": 57.82800100900363 } } } } } } }, "trainer_threads": { "total": 1.3440001112030586e-06, "count": 1, "self": 1.3440001112030586e-06 }, "TrainerController._save_models": { "total": 0.09860924600002363, "count": 1, "self": 0.0011069370000313938, "children": { "RLTrainer._checkpoint": { "total": 0.09750230899999224, "count": 1, "self": 0.09750230899999224 } } } } } } }