{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9660996794700623, "min": 0.9660996794700623, "max": 2.868175983428955, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9181.8115234375, "min": 9181.8115234375, "max": 29278.33984375, "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": 12.956878662109375, "min": 0.3559059500694275, "max": 12.973469734191895, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2526.59130859375, "min": 68.68984985351562, "max": 2646.587890625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06546640424366, "min": 0.06301046795281354, "max": 0.07627590767365558, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26186561697464, "min": 0.25204187181125415, "max": 0.34871732126054006, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.196397227764714, "min": 0.11450982734551834, "max": 0.3037931157093422, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.785588911058856, "min": 0.4580393093820734, "max": 1.5189655785467109, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.98609733800001e-06, "min": 7.98609733800001e-06, "max": 0.00029178600273799997, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.194438935200004e-05, "min": 3.194438935200004e-05, "max": 0.00138468003844, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.102662, "min": 0.102662, "max": 0.19726200000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.410648, "min": 0.410648, "max": 0.96156, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014283380000000017, "min": 0.00014283380000000017, "max": 0.0048633738, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005713352000000007, "min": 0.0005713352000000007, "max": 0.023081844, "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": 25.0, "min": 3.272727272727273, "max": 25.563636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1100.0, "min": 144.0, "max": 1406.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.0, "min": 3.272727272727273, "max": 25.563636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1100.0, "min": 144.0, "max": 1406.0, "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": "1734878454", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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 --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1734878959" }, "total": 505.2832227470001, "count": 1, "self": 0.47543023899993386, "children": { "run_training.setup": { "total": 0.059654108000017914, "count": 1, "self": 0.059654108000017914 }, "TrainerController.start_learning": { "total": 504.74813840000013, "count": 1, "self": 0.5147279780031795, "children": { "TrainerController._reset_env": { "total": 2.1167134160000387, "count": 1, "self": 2.1167134160000387 }, "TrainerController.advance": { "total": 502.02440908499693, "count": 18192, "self": 0.5068890149987055, "children": { "env_step": { "total": 363.4297008039978, "count": 18192, "self": 277.1465201009959, "children": { "SubprocessEnvManager._take_step": { "total": 85.97856617700677, "count": 18192, "self": 1.5728378080216316, "children": { "TorchPolicy.evaluate": { "total": 84.40572836898514, "count": 18192, "self": 84.40572836898514 } } }, "workers": { "total": 0.3046145259951345, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 503.0693739120046, "count": 18192, "is_parallel": true, "self": 262.68007847499655, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028302189999749316, "count": 1, "is_parallel": true, "self": 0.0008542450001414181, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019759739998335135, "count": 10, "is_parallel": true, "self": 0.0019759739998335135 } } }, "UnityEnvironment.step": { "total": 0.04442015299991908, "count": 1, "is_parallel": true, "self": 0.0006880729999920732, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044443599995247496, "count": 1, "is_parallel": true, "self": 0.00044443599995247496 }, "communicator.exchange": { "total": 0.041146540999989156, "count": 1, "is_parallel": true, "self": 0.041146540999989156 }, "steps_from_proto": { "total": 0.002141102999985378, "count": 1, "is_parallel": true, "self": 0.0004748409999137948, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016662620000715833, "count": 10, "is_parallel": true, "self": 0.0016662620000715833 } } } } } } }, "UnityEnvironment.step": { "total": 240.38929543700806, "count": 18191, "is_parallel": true, "self": 11.531342373989673, "children": { "UnityEnvironment._generate_step_input": { "total": 6.3726602550045754, "count": 18191, "is_parallel": true, "self": 6.3726602550045754 }, "communicator.exchange": { "total": 184.61147759501682, "count": 18191, "is_parallel": true, "self": 184.61147759501682 }, "steps_from_proto": { "total": 37.87381521299699, "count": 18191, "is_parallel": true, "self": 7.233340924001254, "children": { "_process_rank_one_or_two_observation": { "total": 30.640474288995733, "count": 181910, "is_parallel": true, "self": 30.640474288995733 } } } } } } } } } } }, "trainer_advance": { "total": 138.08781926600045, "count": 18192, "self": 0.665841511991971, "children": { "process_trajectory": { "total": 31.0816143740077, "count": 18192, "self": 30.653156954007727, "children": { "RLTrainer._checkpoint": { "total": 0.42845741999997244, "count": 4, "self": 0.42845741999997244 } } }, "_update_policy": { "total": 106.34036338000078, "count": 90, "self": 44.366315493005686, "children": { "TorchPPOOptimizer.update": { "total": 61.974047886995095, "count": 4587, "self": 61.974047886995095 } } } } } } }, "trainer_threads": { "total": 1.035999957821332e-06, "count": 1, "self": 1.035999957821332e-06 }, "TrainerController._save_models": { "total": 0.09228688500002136, "count": 1, "self": 0.001217716999917684, "children": { "RLTrainer._checkpoint": { "total": 0.09106916800010367, "count": 1, "self": 0.09106916800010367 } } } } } } }