{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9739418625831604, "min": 0.9739418625831604, "max": 2.866896390914917, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9331.3369140625, "min": 9331.3369140625, "max": 29454.494140625, "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": 12.872129440307617, "min": 0.41358691453933716, "max": 12.872129440307617, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2510.065185546875, "min": 80.2358627319336, "max": 2581.85546875, "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": 0.06860031069278621, "min": 0.06617654776331905, "max": 0.0747166568486921, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27440124277114486, "min": 0.2647061910532762, "max": 0.372320572121466, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2117634826138908, "min": 0.11916757048582476, "max": 0.299558982764389, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8470539304555632, "min": 0.476670281943299, "max": 1.4541599056409564, "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": 25.545454545454547, "min": 3.25, "max": 25.6, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1124.0, "min": 143.0, "max": 1408.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.545454545454547, "min": 3.25, "max": 25.6, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1124.0, "min": 143.0, "max": 1408.0, "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": "1724407493", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/home/leonslzhang/workspace/deep-rl-class/.venv/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1724407771" }, "total": 277.7958323849998, "count": 1, "self": 0.16711632299939083, "children": { "run_training.setup": { "total": 0.018326049000279454, "count": 1, "self": 0.018326049000279454 }, "TrainerController.start_learning": { "total": 277.61039001300014, "count": 1, "self": 0.2925242949841049, "children": { "TrainerController._reset_env": { "total": 0.9105995919999259, "count": 1, "self": 0.9105995919999259 }, "TrainerController.advance": { "total": 276.3540347130165, "count": 18204, "self": 0.1411382920032338, "children": { "env_step": { "total": 276.2128964210133, "count": 18204, "self": 166.4070330169452, "children": { "SubprocessEnvManager._take_step": { "total": 109.66429564505233, "count": 18204, "self": 0.7343646159943091, "children": { "TorchPolicy.evaluate": { "total": 108.92993102905803, "count": 18204, "self": 108.92993102905803 } } }, "workers": { "total": 0.14156775901574292, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 277.07648573194456, "count": 18204, "is_parallel": true, "self": 153.2533017909982, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016711650005163392, "count": 1, "is_parallel": true, "self": 0.0006406160027836449, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010305489977326943, "count": 10, "is_parallel": true, "self": 0.0010305489977326943 } } }, "UnityEnvironment.step": { "total": 0.014845924999463023, "count": 1, "is_parallel": true, "self": 0.00018586999885883415, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00013294600012159208, "count": 1, "is_parallel": true, "self": 0.00013294600012159208 }, "communicator.exchange": { "total": 0.014057667000088259, "count": 1, "is_parallel": true, "self": 0.014057667000088259 }, "steps_from_proto": { "total": 0.0004694420003943378, "count": 1, "is_parallel": true, "self": 0.000127314000565093, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003421279998292448, "count": 10, "is_parallel": true, "self": 0.0003421279998292448 } } } } } } }, "UnityEnvironment.step": { "total": 123.82318394094636, "count": 18203, "is_parallel": true, "self": 2.756135363796602, "children": { "UnityEnvironment._generate_step_input": { "total": 1.538528083023266, "count": 18203, "is_parallel": true, "self": 1.538528083023266 }, "communicator.exchange": { "total": 111.90780550910222, "count": 18203, "is_parallel": true, "self": 111.90780550910222 }, "steps_from_proto": { "total": 7.620714985024279, "count": 18203, "is_parallel": true, "self": 1.6481082002364928, "children": { "_process_rank_one_or_two_observation": { "total": 5.972606784787786, "count": 182030, "is_parallel": true, "self": 5.972606784787786 } } } } } } } } } } } } }, "trainer_threads": { "total": 7.326499962800881e-05, "count": 1, "self": 7.326499962800881e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 275.58798077289157, "count": 248310, "is_parallel": true, "self": 2.5622105668780932, "children": { "process_trajectory": { "total": 154.68356519701047, "count": 248310, "is_parallel": true, "self": 154.3258906940091, "children": { "RLTrainer._checkpoint": { "total": 0.3576745030013626, "count": 4, "is_parallel": true, "self": 0.3576745030013626 } } }, "_update_policy": { "total": 118.34220500900301, "count": 90, "is_parallel": true, "self": 13.91603055599262, "children": { "TorchPPOOptimizer.update": { "total": 104.42617445301039, "count": 4584, "is_parallel": true, "self": 104.42617445301039 } } } } } } } } }, "TrainerController._save_models": { "total": 0.05315814799996588, "count": 1, "self": 0.000371242999790411, "children": { "RLTrainer._checkpoint": { "total": 0.052786905000175466, "count": 1, "self": 0.052786905000175466 } } } } } } }