{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.886394739151001, "min": 0.886394739151001, "max": 2.8600096702575684, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8463.296875, "min": 8463.296875, "max": 29289.359375, "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": 11.849746704101562, "min": 0.4673019349575043, "max": 11.849746704101562, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2310.70068359375, "min": 90.65657806396484, "max": 2403.98828125, "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.Losses.PolicyLoss.mean": { "value": 0.06665187883909847, "min": 0.06269999140332563, "max": 0.07690872628351345, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2666075153563939, "min": 0.25079996561330253, "max": 0.38454363141756726, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19928857004817796, "min": 0.12479077249893225, "max": 0.28496361348558874, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7971542801927118, "min": 0.499163089995729, "max": 1.3835803673547855, "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.CumulativeReward.mean": { "value": 23.954545454545453, "min": 3.477272727272727, "max": 23.954545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1054.0, "min": 153.0, "max": 1270.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.954545454545453, "min": 3.477272727272727, "max": 23.954545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1054.0, "min": 153.0, "max": 1270.0, "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": "1687903780", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "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": "1687904255" }, "total": 475.11599087900004, "count": 1, "self": 0.48803342000019256, "children": { "run_training.setup": { "total": 0.04634765499997684, "count": 1, "self": 0.04634765499997684 }, "TrainerController.start_learning": { "total": 474.58160980399987, "count": 1, "self": 0.5575783010139048, "children": { "TrainerController._reset_env": { "total": 5.1987614019999455, "count": 1, "self": 5.1987614019999455 }, "TrainerController.advance": { "total": 468.68775390398605, "count": 18201, "self": 0.2686924199966825, "children": { "env_step": { "total": 468.41906148398937, "count": 18201, "self": 341.7240884199489, "children": { "SubprocessEnvManager._take_step": { "total": 126.42742768302332, "count": 18201, "self": 1.7790277630386981, "children": { "TorchPolicy.evaluate": { "total": 124.64839991998463, "count": 18201, "self": 124.64839991998463 } } }, "workers": { "total": 0.2675453810171575, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 473.0052322150136, "count": 18201, "is_parallel": true, "self": 221.50899881800945, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006583546000001661, "count": 1, "is_parallel": true, "self": 0.004820471999892106, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017630740001095546, "count": 10, "is_parallel": true, "self": 0.0017630740001095546 } } }, "UnityEnvironment.step": { "total": 0.06047108500001741, "count": 1, "is_parallel": true, "self": 0.0005990979999523915, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000423490999992282, "count": 1, "is_parallel": true, "self": 0.000423490999992282 }, "communicator.exchange": { "total": 0.05723093000005974, "count": 1, "is_parallel": true, "self": 0.05723093000005974 }, "steps_from_proto": { "total": 0.0022175660000129938, "count": 1, "is_parallel": true, "self": 0.00038077199997132993, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018367940000416638, "count": 10, "is_parallel": true, "self": 0.0018367940000416638 } } } } } } }, "UnityEnvironment.step": { "total": 251.49623339700418, "count": 18200, "is_parallel": true, "self": 10.584238124028843, "children": { "UnityEnvironment._generate_step_input": { "total": 5.283277383993777, "count": 18200, "is_parallel": true, "self": 5.283277383993777 }, "communicator.exchange": { "total": 200.52440652799396, "count": 18200, "is_parallel": true, "self": 200.52440652799396 }, "steps_from_proto": { "total": 35.104311360987595, "count": 18200, "is_parallel": true, "self": 6.398166998996771, "children": { "_process_rank_one_or_two_observation": { "total": 28.706144361990823, "count": 182000, "is_parallel": true, "self": 28.706144361990823 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015162199997575954, "count": 1, "self": 0.00015162199997575954, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 465.0879276660878, "count": 463852, "is_parallel": true, "self": 9.648511261154113, "children": { "process_trajectory": { "total": 255.23753725393317, "count": 463852, "is_parallel": true, "self": 254.42350575793296, "children": { "RLTrainer._checkpoint": { "total": 0.8140314960002115, "count": 4, "is_parallel": true, "self": 0.8140314960002115 } } }, "_update_policy": { "total": 200.20187915100053, "count": 90, "is_parallel": true, "self": 78.75912658599339, "children": { "TorchPPOOptimizer.update": { "total": 121.44275256500714, "count": 4587, "is_parallel": true, "self": 121.44275256500714 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13736457499999233, "count": 1, "self": 0.0009363959998154314, "children": { "RLTrainer._checkpoint": { "total": 0.1364281790001769, "count": 1, "self": 0.1364281790001769 } } } } } } }