{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8918144106864929, "min": 0.8875541687011719, "max": 2.8400216102600098, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8593.5234375, "min": 8593.5234375, "max": 29084.662109375, "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": 13.24595832824707, "min": 0.4829676151275635, "max": 13.24595832824707, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2582.9619140625, "min": 93.69571685791016, "max": 2701.99951171875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.09766691158652963, "min": 0.09261211756674802, "max": 0.10999342818075518, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.6836683811057074, "min": 0.5578454722628415, "max": 0.7297949504660133, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18247770608660638, "min": 0.11801026439802215, "max": 0.26355090448776924, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.2773439426062447, "min": 0.7080615863881329, "max": 1.8448563314143849, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.515526066285713e-06, "min": 7.515526066285713e-06, "max": 0.00029238800253733333, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.2608682463999994e-05, "min": 5.2608682463999994e-05, "max": 0.0019466160511279998, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10250514285714285, "min": 0.10250514285714285, "max": 0.19746266666666665, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.717536, "min": 0.717536, "max": 1.348872, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00013500662857142856, "min": 0.00013500662857142856, "max": 0.004873387066666666, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0009450464, "min": 0.0009450464, "max": 0.0324487128, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.522727272727273, "min": 3.6818181818181817, "max": 26.204545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1123.0, "min": 162.0, "max": 1437.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.522727272727273, "min": 3.6818181818181817, "max": 26.204545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1123.0, "min": 162.0, "max": 1437.0, "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": "1715655694", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715656179" }, "total": 485.8909248479997, "count": 1, "self": 0.4897576549997211, "children": { "run_training.setup": { "total": 0.05669901300007041, "count": 1, "self": 0.05669901300007041 }, "TrainerController.start_learning": { "total": 485.3444681799999, "count": 1, "self": 0.6080724949811156, "children": { "TrainerController._reset_env": { "total": 3.0806523189999098, "count": 1, "self": 3.0806523189999098 }, "TrainerController.advance": { "total": 481.56108322101886, "count": 18207, "self": 0.26962616800324213, "children": { "env_step": { "total": 481.2914570530156, "count": 18207, "self": 314.9152442440702, "children": { "SubprocessEnvManager._take_step": { "total": 166.08248510998715, "count": 18207, "self": 1.5460561990016686, "children": { "TorchPolicy.evaluate": { "total": 164.53642891098548, "count": 18207, "self": 164.53642891098548 } } }, "workers": { "total": 0.2937276989582642, "count": 18207, "self": 0.0, "children": { "worker_root": { "total": 483.9750355529584, "count": 18207, "is_parallel": true, "self": 254.98324697394332, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006194940999876053, "count": 1, "is_parallel": true, "self": 0.004353393999735999, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018415470001400536, "count": 10, "is_parallel": true, "self": 0.0018415470001400536 } } }, "UnityEnvironment.step": { "total": 0.039899304000073244, "count": 1, "is_parallel": true, "self": 0.0007557030000953091, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046220300009736093, "count": 1, "is_parallel": true, "self": 0.00046220300009736093 }, "communicator.exchange": { "total": 0.03625619399986135, "count": 1, "is_parallel": true, "self": 0.03625619399986135 }, "steps_from_proto": { "total": 0.002425204000019221, "count": 1, "is_parallel": true, "self": 0.0007225949998428405, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017026090001763805, "count": 10, "is_parallel": true, "self": 0.0017026090001763805 } } } } } } }, "UnityEnvironment.step": { "total": 228.99178857901506, "count": 18206, "is_parallel": true, "self": 10.229315731001634, "children": { "UnityEnvironment._generate_step_input": { "total": 5.407397344018364, "count": 18206, "is_parallel": true, "self": 5.407397344018364 }, "communicator.exchange": { "total": 178.9131883749958, "count": 18206, "is_parallel": true, "self": 178.9131883749958 }, "steps_from_proto": { "total": 34.44188712899927, "count": 18206, "is_parallel": true, "self": 6.564212303038403, "children": { "_process_rank_one_or_two_observation": { "total": 27.877674825960867, "count": 182060, "is_parallel": true, "self": 27.877674825960867 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00024665899991305196, "count": 1, "self": 0.00024665899991305196, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 479.1286263680672, "count": 333590, "is_parallel": true, "self": 7.108257784056377, "children": { "process_trajectory": { "total": 156.21610184601218, "count": 333590, "is_parallel": true, "self": 155.2860475370128, "children": { "RLTrainer._checkpoint": { "total": 0.930054308999388, "count": 4, "is_parallel": true, "self": 0.930054308999388 } } }, "_update_policy": { "total": 315.80426673799866, "count": 138, "is_parallel": true, "self": 65.9532025759986, "children": { "TorchPPOOptimizer.update": { "total": 249.85106416200006, "count": 9243, "is_parallel": true, "self": 249.85106416200006 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09441348600012134, "count": 1, "self": 0.0009682859999884386, "children": { "RLTrainer._checkpoint": { "total": 0.0934452000001329, "count": 1, "self": 0.0934452000001329 } } } } } } }