{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0129594802856445, "min": 1.0129594802856445, "max": 2.8440663814544678, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9627.1669921875, "min": 9627.1669921875, "max": 29032.23046875, "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": 73.54246520996094, "min": 0.3416192829608917, "max": 73.54246520996094, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 14340.78125, "min": 66.27413940429688, "max": 14360.0068359375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.10044643790737894, "min": 0.09383043583652977, "max": 0.10235820637163295, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.40178575162951574, "min": 0.37532174334611906, "max": 0.5117910318581648, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.5154672258843979, "min": 0.12759291470123857, "max": 0.5154672258843979, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 2.0618689035375914, "min": 0.5103716588049543, "max": 2.3671901500692556, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000007e-06, "min": 8.082097306000007e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400003e-05, "min": 3.232838922400003e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269399999999997, "min": 0.10269399999999997, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077599999999986, "min": 0.41077599999999986, "max": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.004864970599999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828000000003, "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": 24.545454545454547, "min": 3.159090909090909, "max": 24.581818181818182, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1080.0, "min": 139.0, "max": 1352.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.545454545454547, "min": 3.159090909090909, "max": 24.581818181818182, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1080.0, "min": 139.0, "max": 1352.0, "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": "1732983025", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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=SnowballTarget3 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1732983711" }, "total": 685.590966522, "count": 1, "self": 0.5273013400001219, "children": { "run_training.setup": { "total": 0.09923942199998237, "count": 1, "self": 0.09923942199998237 }, "TrainerController.start_learning": { "total": 684.9644257599999, "count": 1, "self": 0.6296048209937908, "children": { "TrainerController._reset_env": { "total": 2.2557591730000013, "count": 1, "self": 2.2557591730000013 }, "TrainerController.advance": { "total": 681.9545915940062, "count": 18192, "self": 0.6539497970089769, "children": { "env_step": { "total": 446.865418367983, "count": 18192, "self": 340.13045303899264, "children": { "SubprocessEnvManager._take_step": { "total": 106.36081307498796, "count": 18192, "self": 2.340580594003086, "children": { "TorchPolicy.evaluate": { "total": 104.02023248098487, "count": 18192, "self": 104.02023248098487 } } }, "workers": { "total": 0.3741522540024107, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 683.0483541180116, "count": 18192, "is_parallel": true, "self": 389.6459052540273, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026768310000306883, "count": 1, "is_parallel": true, "self": 0.000812361000043893, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018644699999867953, "count": 10, "is_parallel": true, "self": 0.0018644699999867953 } } }, "UnityEnvironment.step": { "total": 0.08356573499997921, "count": 1, "is_parallel": true, "self": 0.0007236529999090635, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004530240000804042, "count": 1, "is_parallel": true, "self": 0.0004530240000804042 }, "communicator.exchange": { "total": 0.07927014799997778, "count": 1, "is_parallel": true, "self": 0.07927014799997778 }, "steps_from_proto": { "total": 0.003118910000011965, "count": 1, "is_parallel": true, "self": 0.0004334469999776047, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026854630000343604, "count": 10, "is_parallel": true, "self": 0.0026854630000343604 } } } } } } }, "UnityEnvironment.step": { "total": 293.4024488639843, "count": 18191, "is_parallel": true, "self": 14.570775362955715, "children": { "UnityEnvironment._generate_step_input": { "total": 7.904737349003199, "count": 18191, "is_parallel": true, "self": 7.904737349003199 }, "communicator.exchange": { "total": 225.43950179901458, "count": 18191, "is_parallel": true, "self": 225.43950179901458 }, "steps_from_proto": { "total": 45.487434353010826, "count": 18191, "is_parallel": true, "self": 8.652816293999877, "children": { "_process_rank_one_or_two_observation": { "total": 36.83461805901095, "count": 181910, "is_parallel": true, "self": 36.83461805901095 } } } } } } } } } } }, "trainer_advance": { "total": 234.43522342901417, "count": 18192, "self": 0.8372935750144279, "children": { "process_trajectory": { "total": 38.63419168700079, "count": 18192, "self": 38.169216137001285, "children": { "RLTrainer._checkpoint": { "total": 0.4649755499995081, "count": 4, "self": 0.4649755499995081 } } }, "_update_policy": { "total": 194.96373816699895, "count": 90, "self": 51.316157126001485, "children": { "TorchPPOOptimizer.update": { "total": 143.64758104099747, "count": 9177, "self": 143.64758104099747 } } } } } } }, "trainer_threads": { "total": 1.6430001323897159e-06, "count": 1, "self": 1.6430001323897159e-06 }, "TrainerController._save_models": { "total": 0.12446852899984151, "count": 1, "self": 0.001158765999662137, "children": { "RLTrainer._checkpoint": { "total": 0.12330976300017937, "count": 1, "self": 0.12330976300017937 } } } } } } }