{ "name": "root", "gauges": { "ShooterBasic.Policy.Entropy.mean": { "value": 1.4824821949005127, "min": 1.0895097255706787, "max": 2.638326644897461, "count": 250 }, "ShooterBasic.Policy.Entropy.sum": { "value": 2963.48193359375, "min": 2180.10888671875, "max": 5279.29150390625, "count": 250 }, "ShooterBasic.Step.mean": { "value": 499998.0, "min": 1998.0, "max": 499998.0, "count": 250 }, "ShooterBasic.Step.sum": { "value": 499998.0, "min": 1998.0, "max": 499998.0, "count": 250 }, "ShooterBasic.Policy.ExtrinsicValueEstimate.mean": { "value": -0.006963093765079975, "min": -0.21738854050636292, "max": 0.023092469200491905, "count": 250 }, "ShooterBasic.Policy.ExtrinsicValueEstimate.sum": { "value": -4.644383430480957, "min": -145.86770629882812, "max": 15.402676582336426, "count": 250 }, "ShooterBasic.Losses.PolicyLoss.mean": { "value": 0.12747625884852218, "min": 0.10908348486797573, "max": 0.15455300048051868, "count": 250 }, "ShooterBasic.Losses.PolicyLoss.sum": { "value": 1.0198100707881774, "min": 0.786331330309622, "max": 1.2364240038441494, "count": 250 }, "ShooterBasic.Losses.ValueLoss.mean": { "value": 9.136862847934173e-07, "min": 5.960540469066948e-08, "max": 0.02674982081483298, "count": 250 }, "ShooterBasic.Losses.ValueLoss.sum": { "value": 7.309490278347338e-06, "min": 4.768432375253558e-07, "max": 0.21399856651866384, "count": 250 }, "ShooterBasic.Policy.LearningRate.mean": { "value": 5.972498009499977e-07, "min": 5.972498009499977e-07, "max": 0.00029938080020639997, "count": 250 }, "ShooterBasic.Policy.LearningRate.sum": { "value": 4.777998407599982e-06, "min": 4.777998407599982e-06, "max": 0.0023857572047476, "count": 250 }, "ShooterBasic.Policy.Epsilon.mean": { "value": 0.10019905000000001, "min": 0.10019905000000001, "max": 0.19979360000000002, "count": 250 }, "ShooterBasic.Policy.Epsilon.sum": { "value": 0.8015924000000001, "min": 0.7069943999999999, "max": 1.5952524000000001, "count": 250 }, "ShooterBasic.Policy.Beta.mean": { "value": 1.9932594999999962e-05, "min": 1.9932594999999962e-05, "max": 0.00498970064, "count": 250 }, "ShooterBasic.Policy.Beta.sum": { "value": 0.0001594607599999997, "min": 0.0001594607599999997, "max": 0.039763094760000006, "count": 250 }, "ShooterBasic.Environment.EpisodeLength.mean": { "value": 2499.0, "min": 31.161290322580644, "max": 2499.0, "count": 205 }, "ShooterBasic.Environment.EpisodeLength.sum": { "value": 2499.0, "min": 146.0, "max": 4250.0, "count": 205 }, "ShooterBasic.Environment.CumulativeReward.mean": { "value": -0.9995999505044892, "min": -2.879599778330885, "max": 1.8279999308288097, "count": 205 }, "ShooterBasic.Environment.CumulativeReward.sum": { "value": -0.9995999505044892, "min": -63.19960029050708, "max": 2.3895999547094107, "count": 205 }, "ShooterBasic.Policy.ExtrinsicReward.mean": { "value": -0.9995999505044892, "min": -2.879599778330885, "max": 1.8279999308288097, "count": 205 }, "ShooterBasic.Policy.ExtrinsicReward.sum": { "value": -0.9995999505044892, "min": -63.19960029050708, "max": 2.3895999547094107, "count": 205 }, "ShooterBasic.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 250 }, "ShooterBasic.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 250 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1692209791", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/ShooterOrange.yaml --env=./training-envs-executables/linux/Shooter_00/Shooter_00 --run-id=Shooter01 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1692212778" }, "total": 2987.562962117, "count": 1, "self": 0.5939823600001546, "children": { "run_training.setup": { "total": 0.0525785629999973, "count": 1, "self": 0.0525785629999973 }, "TrainerController.start_learning": { "total": 2986.916401194, "count": 1, "self": 11.806434428058765, "children": { "TrainerController._reset_env": { "total": 1.626698766000004, "count": 1, "self": 1.626698766000004 }, "TrainerController.advance": { "total": 2973.3964364819412, "count": 500309, "self": 10.706079446877084, "children": { "env_step": { "total": 2362.8686963399596, "count": 500309, "self": 1719.2106472249543, "children": { "SubprocessEnvManager._take_step": { "total": 636.6136659698503, "count": 500309, "self": 33.50798116086196, "children": { "TorchPolicy.evaluate": { "total": 603.1056848089884, "count": 500001, "self": 603.1056848089884 } } }, "workers": { "total": 7.044383145154939, "count": 500309, "self": 0.0, "children": { "worker_root": { "total": 2965.624904697787, "count": 500309, "is_parallel": true, "self": 1816.9000337049486, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005608940999991319, "count": 1, "is_parallel": true, "self": 0.0048137390000420055, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007952019999493132, "count": 4, "is_parallel": true, "self": 0.0007952019999493132 } } }, "UnityEnvironment.step": { "total": 0.026568327000006775, "count": 1, "is_parallel": true, "self": 0.0001840620000166382, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024291500000117594, "count": 1, "is_parallel": true, "self": 0.00024291500000117594 }, "communicator.exchange": { "total": 0.025493911000012304, "count": 1, "is_parallel": true, "self": 0.025493911000012304 }, "steps_from_proto": { "total": 0.0006474389999766572, "count": 1, "is_parallel": true, "self": 0.0003238440000359333, "children": { "_process_rank_one_or_two_observation": { "total": 0.00032359499994072394, "count": 4, "is_parallel": true, "self": 0.00032359499994072394 } } } } } } }, "UnityEnvironment.step": { "total": 1148.7248709928383, "count": 500308, "is_parallel": true, "self": 53.21501695778875, "children": { "UnityEnvironment._generate_step_input": { "total": 42.855336293951666, "count": 500308, "is_parallel": true, "self": 42.855336293951666 }, "communicator.exchange": { "total": 823.2242927070469, "count": 500308, "is_parallel": true, "self": 823.2242927070469 }, "steps_from_proto": { "total": 229.43022503405103, "count": 500308, "is_parallel": true, "self": 126.35356219302241, "children": { "_process_rank_one_or_two_observation": { "total": 103.07666284102862, "count": 2001232, "is_parallel": true, "self": 103.07666284102862 } } } } } } } } } } }, "trainer_advance": { "total": 599.8216606951044, "count": 500309, "self": 12.822596677169713, "children": { "process_trajectory": { "total": 259.8214377189371, "count": 500309, "self": 259.6711001989371, "children": { "RLTrainer._checkpoint": { "total": 0.15033751999999367, "count": 1, "self": 0.15033751999999367 } } }, "_update_policy": { "total": 327.1776262989976, "count": 1937, "self": 126.58520726297724, "children": { "TorchPPOOptimizer.update": { "total": 200.59241903602037, "count": 46488, "self": 200.59241903602037 } } } } } } }, "trainer_threads": { "total": 1.1980000635958277e-06, "count": 1, "self": 1.1980000635958277e-06 }, "TrainerController._save_models": { "total": 0.08683031999999002, "count": 1, "self": 0.0005780699998467753, "children": { "RLTrainer._checkpoint": { "total": 0.08625225000014325, "count": 1, "self": 0.08625225000014325 } } } } } } }