{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.949543833732605, "min": 0.949543833732605, "max": 2.8719568252563477, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9076.689453125, "min": 9076.689453125, "max": 29411.708984375, "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": 12.531420707702637, "min": 0.25959312915802, "max": 12.531420707702637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2443.626953125, "min": 50.36106491088867, "max": 2534.479248046875, "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": 0.06499442938266108, "min": 0.06415400516843696, "max": 0.07251160284806032, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2599777175306443, "min": 0.25661602067374784, "max": 0.35635102004173447, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2031729436096023, "min": 0.10557009149274296, "max": 0.27052688166206956, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8126917744384092, "min": 0.42228036597097185, "max": 1.3526344083103479, "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": 2.9545454545454546, "max": 25.204545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1097.0, "min": 130.0, "max": 1376.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.931818181818183, "min": 2.9545454545454546, "max": 25.204545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1097.0, "min": 130.0, "max": 1376.0, "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": "1690633995", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690634472" }, "total": 477.60347952099994, "count": 1, "self": 0.4390994509999473, "children": { "run_training.setup": { "total": 0.03794004499991388, "count": 1, "self": 0.03794004499991388 }, "TrainerController.start_learning": { "total": 477.1264400250001, "count": 1, "self": 0.5524731889820487, "children": { "TrainerController._reset_env": { "total": 5.641154912000047, "count": 1, "self": 5.641154912000047 }, "TrainerController.advance": { "total": 470.79082253201784, "count": 18201, "self": 0.2816474300217351, "children": { "env_step": { "total": 470.5091751019961, "count": 18201, "self": 342.4534570449756, "children": { "SubprocessEnvManager._take_step": { "total": 127.75935844202354, "count": 18201, "self": 1.8735878240200918, "children": { "TorchPolicy.evaluate": { "total": 125.88577061800345, "count": 18201, "self": 125.88577061800345 } } }, "workers": { "total": 0.29635961499695895, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 475.54012874901036, "count": 18201, "is_parallel": true, "self": 227.05449274102205, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005554537999955755, "count": 1, "is_parallel": true, "self": 0.003921996999793009, "children": { "_process_rank_one_or_two_observation": { "total": 0.001632541000162746, "count": 10, "is_parallel": true, "self": 0.001632541000162746 } } }, "UnityEnvironment.step": { "total": 0.10555301900001268, "count": 1, "is_parallel": true, "self": 0.000737909999884323, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040894400001434406, "count": 1, "is_parallel": true, "self": 0.00040894400001434406 }, "communicator.exchange": { "total": 0.09478786900001523, "count": 1, "is_parallel": true, "self": 0.09478786900001523 }, "steps_from_proto": { "total": 0.00961829600009878, "count": 1, "is_parallel": true, "self": 0.007552055000132896, "children": { "_process_rank_one_or_two_observation": { "total": 0.002066240999965885, "count": 10, "is_parallel": true, "self": 0.002066240999965885 } } } } } } }, "UnityEnvironment.step": { "total": 248.48563600798832, "count": 18200, "is_parallel": true, "self": 10.888960772994892, "children": { "UnityEnvironment._generate_step_input": { "total": 5.2862072029884075, "count": 18200, "is_parallel": true, "self": 5.2862072029884075 }, "communicator.exchange": { "total": 196.5673141339969, "count": 18200, "is_parallel": true, "self": 196.5673141339969 }, "steps_from_proto": { "total": 35.74315389800813, "count": 18200, "is_parallel": true, "self": 6.684635039995101, "children": { "_process_rank_one_or_two_observation": { "total": 29.05851885801303, "count": 182000, "is_parallel": true, "self": 29.05851885801303 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016570100001445098, "count": 1, "self": 0.00016570100001445098, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 467.14113712906305, "count": 438907, "is_parallel": true, "self": 9.947901987076534, "children": { "process_trajectory": { "total": 255.5070546269867, "count": 438907, "is_parallel": true, "self": 254.34963273698668, "children": { "RLTrainer._checkpoint": { "total": 1.1574218900000233, "count": 4, "is_parallel": true, "self": 1.1574218900000233 } } }, "_update_policy": { "total": 201.68618051499982, "count": 90, "is_parallel": true, "self": 78.83597765699403, "children": { "TorchPPOOptimizer.update": { "total": 122.85020285800579, "count": 4584, "is_parallel": true, "self": 122.85020285800579 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14182369100012693, "count": 1, "self": 0.0010235120000743336, "children": { "RLTrainer._checkpoint": { "total": 0.1408001790000526, "count": 1, "self": 0.1408001790000526 } } } } } } }