{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9445054531097412, "min": 0.9445054531097412, "max": 2.8683905601501465, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9049.306640625, "min": 9049.306640625, "max": 29375.1875, "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": 12.851655960083008, "min": 0.39808371663093567, "max": 12.851655960083008, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2506.072998046875, "min": 77.22824096679688, "max": 2596.91015625, "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": 0.06674373529477082, "min": 0.06125816749553291, "max": 0.07429374036648512, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26697494117908327, "min": 0.24503266998213163, "max": 0.3629310035486888, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19822918864734032, "min": 0.10663014946404992, "max": 0.27999431362339094, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7929167545893613, "min": 0.42652059785619967, "max": 1.3999715681169547, "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": 25.636363636363637, "min": 3.25, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1128.0, "min": 143.0, "max": 1391.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.636363636363637, "min": 3.25, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1128.0, "min": 143.0, "max": 1391.0, "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": "1676469896", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "command_line_arguments": "/home/jamesup/Documents/source/deep-rl-class/env/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./envs/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cu116", "numpy_version": "1.23.3", "end_time_seconds": "1676470443" }, "total": 546.9981194689753, "count": 1, "self": 0.37385836301837116, "children": { "run_training.setup": { "total": 0.10256792698055506, "count": 1, "self": 0.10256792698055506 }, "TrainerController.start_learning": { "total": 546.5216931789764, "count": 1, "self": 0.5916225896799006, "children": { "TrainerController._reset_env": { "total": 2.9304936209809966, "count": 1, "self": 2.9304936209809966 }, "TrainerController.advance": { "total": 542.8845941133332, "count": 18204, "self": 0.2605801362078637, "children": { "env_step": { "total": 542.6240139771253, "count": 18204, "self": 309.889693603036, "children": { "SubprocessEnvManager._take_step": { "total": 232.4639638143126, "count": 18204, "self": 1.6493766648345627, "children": { "TorchPolicy.evaluate": { "total": 230.81458714947803, "count": 18204, "self": 126.91559281660011, "children": { "TorchPolicy.sample_actions": { "total": 103.89899433287792, "count": 18204, "self": 103.89899433287792 } } } } }, "workers": { "total": 0.27035655977670103, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 545.8072018221719, "count": 18204, "is_parallel": true, "self": 329.4239262812771, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022838369477540255, "count": 1, "is_parallel": true, "self": 0.001038589864037931, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012452470837160945, "count": 10, "is_parallel": true, "self": 0.0012452470837160945 } } }, "UnityEnvironment.step": { "total": 0.02487535198451951, "count": 1, "is_parallel": true, "self": 0.0003944619675166905, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00028765801107510924, "count": 1, "is_parallel": true, "self": 0.00028765801107510924 }, "communicator.exchange": { "total": 0.023062668973580003, "count": 1, "is_parallel": true, "self": 0.023062668973580003 }, "steps_from_proto": { "total": 0.001130563032347709, "count": 1, "is_parallel": true, "self": 0.0002476570080034435, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008829060243442655, "count": 10, "is_parallel": true, "self": 0.0008829060243442655 } } } } } } }, "UnityEnvironment.step": { "total": 216.38327554089483, "count": 18203, "is_parallel": true, "self": 10.170859139761887, "children": { "UnityEnvironment._generate_step_input": { "total": 5.658544852223713, "count": 18203, "is_parallel": true, "self": 5.658544852223713 }, "communicator.exchange": { "total": 172.50128052994842, "count": 18203, "is_parallel": true, "self": 172.50128052994842 }, "steps_from_proto": { "total": 28.05259101896081, "count": 18203, "is_parallel": true, "self": 5.696868360799272, "children": { "_process_rank_one_or_two_observation": { "total": 22.35572265816154, "count": 182030, "is_parallel": true, "self": 22.35572265816154 } } } } } } } } } } } } }, "trainer_threads": { "total": 8.485297439619899e-05, "count": 1, "self": 8.485297439619899e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 539.7179365857155, "count": 667414, "is_parallel": true, "self": 8.760390451643616, "children": { "process_trajectory": { "total": 307.11614359129453, "count": 667414, "is_parallel": true, "self": 306.53249749325914, "children": { "RLTrainer._checkpoint": { "total": 0.5836460980353877, "count": 4, "is_parallel": true, "self": 0.5836460980353877 } } }, "_update_policy": { "total": 223.84140254277736, "count": 90, "is_parallel": true, "self": 33.35419784625992, "children": { "TorchPPOOptimizer.update": { "total": 190.48720469651744, "count": 4587, "is_parallel": true, "self": 190.48720469651744 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11489800200797617, "count": 1, "self": 0.0006774410139769316, "children": { "RLTrainer._checkpoint": { "total": 0.11422056099399924, "count": 1, "self": 0.11422056099399924 } } } } } } }