{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8160935640335083, "min": 0.8160935640335083, "max": 2.8763952255249023, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7801.03857421875, "min": 7801.03857421875, "max": 29457.1640625, "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": 12.404738426208496, "min": 0.09431944042444229, "max": 12.404738426208496, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2418.924072265625, "min": 18.297971725463867, "max": 2505.81689453125, "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": 0.06716097880787714, "min": 0.05975955095365826, "max": 0.0760964329637514, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26864391523150855, "min": 0.26829367886724265, "max": 0.35333789267614896, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22361233815842985, "min": 0.10862591384690913, "max": 0.28650397580920484, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8944493526337194, "min": 0.4345036553876365, "max": 1.314941291423405, "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": 24.931818181818183, "min": 2.7954545454545454, "max": 24.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1097.0, "min": 123.0, "max": 1343.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.931818181818183, "min": 2.7954545454545454, "max": 24.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1097.0, "min": 123.0, "max": 1343.0, "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": "1691248082", "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/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": "1691248542" }, "total": 459.22485641799994, "count": 1, "self": 0.3880700039999283, "children": { "run_training.setup": { "total": 0.04429154800004653, "count": 1, "self": 0.04429154800004653 }, "TrainerController.start_learning": { "total": 458.79249486599997, "count": 1, "self": 0.5413382959950468, "children": { "TrainerController._reset_env": { "total": 5.795957205999912, "count": 1, "self": 5.795957205999912 }, "TrainerController.advance": { "total": 452.3176085900052, "count": 18202, "self": 0.25518145099658796, "children": { "env_step": { "total": 452.0624271390086, "count": 18202, "self": 328.97447856898793, "children": { "SubprocessEnvManager._take_step": { "total": 122.81767790802087, "count": 18202, "self": 1.7219467170266398, "children": { "TorchPolicy.evaluate": { "total": 121.09573119099423, "count": 18202, "self": 121.09573119099423 } } }, "workers": { "total": 0.27027066199980254, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 457.3751434760211, "count": 18202, "is_parallel": true, "self": 217.85280836401944, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006513049000204774, "count": 1, "is_parallel": true, "self": 0.0049325680004130845, "children": { "_process_rank_one_or_two_observation": { "total": 0.001580480999791689, "count": 10, "is_parallel": true, "self": 0.001580480999791689 } } }, "UnityEnvironment.step": { "total": 0.05033420999984628, "count": 1, "is_parallel": true, "self": 0.0006328750000648142, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004111109999485052, "count": 1, "is_parallel": true, "self": 0.0004111109999485052 }, "communicator.exchange": { "total": 0.04715193799984263, "count": 1, "is_parallel": true, "self": 0.04715193799984263 }, "steps_from_proto": { "total": 0.0021382859999903303, "count": 1, "is_parallel": true, "self": 0.000380622000193398, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017576639997969323, "count": 10, "is_parallel": true, "self": 0.0017576639997969323 } } } } } } }, "UnityEnvironment.step": { "total": 239.52233511200166, "count": 18201, "is_parallel": true, "self": 10.278272333993982, "children": { "UnityEnvironment._generate_step_input": { "total": 5.160837431999653, "count": 18201, "is_parallel": true, "self": 5.160837431999653 }, "communicator.exchange": { "total": 189.05232621399387, "count": 18201, "is_parallel": true, "self": 189.05232621399387 }, "steps_from_proto": { "total": 35.030899132014156, "count": 18201, "is_parallel": true, "self": 6.269141282073406, "children": { "_process_rank_one_or_two_observation": { "total": 28.76175784994075, "count": 182010, "is_parallel": true, "self": 28.76175784994075 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012072599997736688, "count": 1, "self": 0.00012072599997736688, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 448.9573716419966, "count": 417779, "is_parallel": true, "self": 9.5832699669661, "children": { "process_trajectory": { "total": 243.73637044503016, "count": 417779, "is_parallel": true, "self": 242.97910553303018, "children": { "RLTrainer._checkpoint": { "total": 0.7572649119999824, "count": 4, "is_parallel": true, "self": 0.7572649119999824 } } }, "_update_policy": { "total": 195.63773123000033, "count": 90, "is_parallel": true, "self": 77.16906431400344, "children": { "TorchPPOOptimizer.update": { "total": 118.46866691599689, "count": 4587, "is_parallel": true, "self": 118.46866691599689 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13747004799984097, "count": 1, "self": 0.0008989279997422273, "children": { "RLTrainer._checkpoint": { "total": 0.13657112000009874, "count": 1, "self": 0.13657112000009874 } } } } } } }