{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8264872431755066, "min": 0.8264872431755066, "max": 2.8455417156219482, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7854.9345703125, "min": 7854.9345703125, "max": 29047.2890625, "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": 13.163208961486816, "min": 0.4072156250476837, "max": 13.163208961486816, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2566.82568359375, "min": 78.99983215332031, "max": 2647.6982421875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07193693158835374, "min": 0.0646662844332419, "max": 0.0737180728368306, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28774772635341495, "min": 0.2695292332643351, "max": 0.3684069567719359, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1815802675544047, "min": 0.11381821694792997, "max": 0.29465975895816204, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7263210702176188, "min": 0.4552728677917199, "max": 1.4732987947908103, "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.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.Environment.CumulativeReward.mean": { "value": 26.15909090909091, "min": 3.1363636363636362, "max": 26.15909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1151.0, "min": 138.0, "max": 1423.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.15909090909091, "min": 3.1363636363636362, "max": 26.15909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1151.0, "min": 138.0, "max": 1423.0, "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": "1783818211", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1783818678" }, "total": 466.979920836, "count": 1, "self": 0.6905248839998421, "children": { "run_training.setup": { "total": 0.02721301300016421, "count": 1, "self": 0.02721301300016421 }, "TrainerController.start_learning": { "total": 466.262182939, "count": 1, "self": 0.38049125894940516, "children": { "TrainerController._reset_env": { "total": 3.3083290899999156, "count": 1, "self": 3.3083290899999156 }, "TrainerController.advance": { "total": 462.4599062490506, "count": 18192, "self": 0.40316871204049676, "children": { "env_step": { "total": 341.84256262400186, "count": 18192, "self": 267.9251861399948, "children": { "SubprocessEnvManager._take_step": { "total": 73.68789697398415, "count": 18192, "self": 1.322181095011274, "children": { "TorchPolicy.evaluate": { "total": 72.36571587897288, "count": 18192, "self": 72.36571587897288 } } }, "workers": { "total": 0.22947951002288391, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 464.2215694160318, "count": 18192, "is_parallel": true, "self": 228.855221052027, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004629175999980362, "count": 1, "is_parallel": true, "self": 0.0032376969998040295, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013914790001763322, "count": 10, "is_parallel": true, "self": 0.0013914790001763322 } } }, "UnityEnvironment.step": { "total": 0.07219427199970596, "count": 1, "is_parallel": true, "self": 0.0006187189997035603, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004425309998623561, "count": 1, "is_parallel": true, "self": 0.0004425309998623561 }, "communicator.exchange": { "total": 0.06913689800012435, "count": 1, "is_parallel": true, "self": 0.06913689800012435 }, "steps_from_proto": { "total": 0.0019961240000156977, "count": 1, "is_parallel": true, "self": 0.00040658000034454744, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015895439996711502, "count": 10, "is_parallel": true, "self": 0.0015895439996711502 } } } } } } }, "UnityEnvironment.step": { "total": 235.3663483640048, "count": 18191, "is_parallel": true, "self": 10.695092840991947, "children": { "UnityEnvironment._generate_step_input": { "total": 5.589860008001779, "count": 18191, "is_parallel": true, "self": 5.589860008001779 }, "communicator.exchange": { "total": 180.25362043896803, "count": 18191, "is_parallel": true, "self": 180.25362043896803 }, "steps_from_proto": { "total": 38.827775076043054, "count": 18191, "is_parallel": true, "self": 6.8767133109904535, "children": { "_process_rank_one_or_two_observation": { "total": 31.9510617650526, "count": 181910, "is_parallel": true, "self": 31.9510617650526 } } } } } } } } } } }, "trainer_advance": { "total": 120.21417491300826, "count": 18192, "self": 0.4700617690600666, "children": { "process_trajectory": { "total": 24.650673496947093, "count": 18192, "self": 24.189492893947317, "children": { "RLTrainer._checkpoint": { "total": 0.46118060299977515, "count": 4, "self": 0.46118060299977515 } } }, "_update_policy": { "total": 95.0934396470011, "count": 90, "self": 38.301524623987916, "children": { "TorchPPOOptimizer.update": { "total": 56.79191502301319, "count": 4587, "self": 56.79191502301319 } } } } } } }, "trainer_threads": { "total": 1.3280000530357938e-06, "count": 1, "self": 1.3280000530357938e-06 }, "TrainerController._save_models": { "total": 0.1134550130000207, "count": 1, "self": 0.0008746590001464938, "children": { "RLTrainer._checkpoint": { "total": 0.1125803539998742, "count": 1, "self": 0.1125803539998742 } } } } } } }