{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9451347589492798, "min": 0.9451347589492798, "max": 2.888890504837036, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9065.732421875, "min": 9065.732421875, "max": 29558.0234375, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.03701400756836, "min": -0.029289813712239265, "max": 13.03701400756836, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2672.587890625, "min": -5.682223796844482, "max": 2672.587890625, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.727272727272727, "min": 2.727272727272727, "max": 26.074074074074073, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1415.0, "min": 120.0, "max": 1433.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.727272727272727, "min": 2.727272727272727, "max": 26.074074074074073, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1415.0, "min": 120.0, "max": 1433.0, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.03296543655204575, "min": 0.02496469756086156, "max": 0.04126192483589893, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.03296543655204575, "min": 0.02496469756086156, "max": 0.07246377125985043, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2154506921183829, "min": 0.09163210131958419, "max": 0.3294458009448706, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.2154506921183829, "min": 0.09163210131958419, "max": 0.5970499179526871, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 4.37289854240001e-06, "min": 4.37289854240001e-06, "max": 0.00029477280174239996, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 4.37289854240001e-06, "min": 4.37289854240001e-06, "max": 0.0005103456298848, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10145760000000001, "min": 0.10145760000000001, "max": 0.19825759999999998, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.10145760000000001, "min": 0.10145760000000001, "max": 0.3701152, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 8.273424000000016e-05, "min": 8.273424000000016e-05, "max": 0.00491305424, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 8.273424000000016e-05, "min": 8.273424000000016e-05, "max": 0.008508748480000002, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701031875", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/home/dfotland/projects/wsl-reinforce/ml-agents/venv-agents/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTargetWSL1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701033380" }, "total": 1505.3442897149944, "count": 1, "self": 0.1675799140066374, "children": { "run_training.setup": { "total": 0.006960844999412075, "count": 1, "self": 0.006960844999412075 }, "TrainerController.start_learning": { "total": 1505.1697489559883, "count": 1, "self": 0.4516628522251267, "children": { "TrainerController._reset_env": { "total": 0.738570471003186, "count": 1, "self": 0.738570471003186 }, "TrainerController.advance": { "total": 1503.7972513727436, "count": 45464, "self": 0.43274122750153765, "children": { "env_step": { "total": 1274.305056270794, "count": 45464, "self": 342.1040422723454, "children": { "SubprocessEnvManager._take_step": { "total": 931.8898526579433, "count": 45464, "self": 1.655462255119346, "children": { "TorchPolicy.evaluate": { "total": 930.2343904028239, "count": 45464, "self": 930.2343904028239 } } }, "workers": { "total": 0.3111613405053504, "count": 45464, "self": 0.0, "children": { "worker_root": { "total": 1503.4036772572435, "count": 45464, "is_parallel": true, "self": 1191.1151526636386, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011073779896833003, "count": 1, "is_parallel": true, "self": 0.000328516005538404, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007788619841448963, "count": 10, "is_parallel": true, "self": 0.0007788619841448963 } } }, "UnityEnvironment.step": { "total": 0.013996214984217659, "count": 1, "is_parallel": true, "self": 0.00014994796947576106, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00013590999878942966, "count": 1, "is_parallel": true, "self": 0.00013590999878942966 }, "communicator.exchange": { "total": 0.01327719000983052, "count": 1, "is_parallel": true, "self": 0.01327719000983052 }, "steps_from_proto": { "total": 0.00043316700612194836, "count": 1, "is_parallel": true, "self": 9.82559286057949e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.00033491107751615345, "count": 10, "is_parallel": true, "self": 0.00033491107751615345 } } } } } } }, "UnityEnvironment.step": { "total": 312.28852459360496, "count": 45463, "is_parallel": true, "self": 6.711575365741737, "children": { "UnityEnvironment._generate_step_input": { "total": 3.7437563616549596, "count": 45463, "is_parallel": true, "self": 3.7437563616549596 }, "communicator.exchange": { "total": 283.55116693637683, "count": 45463, "is_parallel": true, "self": 283.55116693637683 }, "steps_from_proto": { "total": 18.282025929831434, "count": 45463, "is_parallel": true, "self": 3.854859669954749, "children": { "_process_rank_one_or_two_observation": { "total": 14.427166259876685, "count": 454630, "is_parallel": true, "self": 14.427166259876685 } } } } } } } } } } }, "trainer_advance": { "total": 229.05945387444808, "count": 45464, "self": 0.5758158160315361, "children": { "process_trajectory": { "total": 121.48779294436099, "count": 45464, "self": 120.10247636539862, "children": { "RLTrainer._checkpoint": { "total": 1.3853165789623745, "count": 10, "self": 1.3853165789623745 } } }, "_update_policy": { "total": 106.99584511405556, "count": 56, "self": 34.16995892339037, "children": { "TorchPPOOptimizer.update": { "total": 72.82588619066519, "count": 2856, "self": 72.82588619066519 } } } } } } }, "trainer_threads": { "total": 5.100155249238014e-07, "count": 1, "self": 5.100155249238014e-07 }, "TrainerController._save_models": { "total": 0.18226375000085682, "count": 1, "self": 0.0003407559997867793, "children": { "RLTrainer._checkpoint": { "total": 0.18192299400107004, "count": 1, "self": 0.18192299400107004 } } } } } } }