{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8819518685340881, "min": 0.8819518685340881, "max": 2.8172922134399414, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8382.0703125, "min": 8382.0703125, "max": 28758.91796875, "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": 13.16395378112793, "min": 0.463492214679718, "max": 13.16395378112793, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2566.970947265625, "min": 89.91748809814453, "max": 2647.45263671875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06213292415572248, "min": 0.06213292415572248, "max": 0.07353301648040275, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24853169662288993, "min": 0.24853169662288993, "max": 0.3664188628916985, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1786963776411379, "min": 0.1786963776411379, "max": 0.2980266838681464, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7147855105645516, "min": 0.7147855105645516, "max": 1.4210609887160508, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082009730600007e-05, "min": 8.082009730600007e-05, "max": 0.0029188200027059994, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00032328038922400026, "min": 0.00032328038922400026, "max": 0.013851600038280001, "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": 26.09090909090909, "min": 4.136363636363637, "max": 26.09090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1148.0, "min": 182.0, "max": 1417.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.09090909090909, "min": 4.136363636363637, "max": 26.09090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1148.0, "min": 182.0, "max": 1417.0, "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": "1767027801", "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": "1767028236" }, "total": 434.64083709500005, "count": 1, "self": 0.4861635700001443, "children": { "run_training.setup": { "total": 0.03310143799990328, "count": 1, "self": 0.03310143799990328 }, "TrainerController.start_learning": { "total": 434.121572087, "count": 1, "self": 0.3884296000012455, "children": { "TrainerController._reset_env": { "total": 3.4292032760001803, "count": 1, "self": 3.4292032760001803 }, "TrainerController.advance": { "total": 430.22762986599855, "count": 18192, "self": 0.3789794580054604, "children": { "env_step": { "total": 311.4577288189928, "count": 18192, "self": 244.02673592098404, "children": { "SubprocessEnvManager._take_step": { "total": 67.21707412001228, "count": 18192, "self": 1.2312931510050475, "children": { "TorchPolicy.evaluate": { "total": 65.98578096900724, "count": 18192, "self": 65.98578096900724 } } }, "workers": { "total": 0.21391877799646863, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 432.36279958998125, "count": 18192, "is_parallel": true, "self": 217.94583663499543, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00774580799998148, "count": 1, "is_parallel": true, "self": 0.004475902000422138, "children": { "_process_rank_one_or_two_observation": { "total": 0.0032699059995593416, "count": 10, "is_parallel": true, "self": 0.0032699059995593416 } } }, "UnityEnvironment.step": { "total": 0.03473234600005526, "count": 1, "is_parallel": true, "self": 0.0006319290002920752, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003936879998036602, "count": 1, "is_parallel": true, "self": 0.0003936879998036602 }, "communicator.exchange": { "total": 0.031464139000036084, "count": 1, "is_parallel": true, "self": 0.031464139000036084 }, "steps_from_proto": { "total": 0.002242589999923439, "count": 1, "is_parallel": true, "self": 0.0006964349997815589, "children": { "_process_rank_one_or_two_observation": { "total": 0.00154615500014188, "count": 10, "is_parallel": true, "self": 0.00154615500014188 } } } } } } }, "UnityEnvironment.step": { "total": 214.41696295498582, "count": 18191, "is_parallel": true, "self": 10.072814563980046, "children": { "UnityEnvironment._generate_step_input": { "total": 5.274239174993454, "count": 18191, "is_parallel": true, "self": 5.274239174993454 }, "communicator.exchange": { "total": 164.18583801198997, "count": 18191, "is_parallel": true, "self": 164.18583801198997 }, "steps_from_proto": { "total": 34.88407120402235, "count": 18191, "is_parallel": true, "self": 6.368252932066525, "children": { "_process_rank_one_or_two_observation": { "total": 28.515818271955823, "count": 181910, "is_parallel": true, "self": 28.515818271955823 } } } } } } } } } } }, "trainer_advance": { "total": 118.3909215890003, "count": 18192, "self": 0.4735052600005929, "children": { "process_trajectory": { "total": 25.51429580499962, "count": 18192, "self": 24.99221179799997, "children": { "RLTrainer._checkpoint": { "total": 0.5220840069996484, "count": 4, "self": 0.5220840069996484 } } }, "_update_policy": { "total": 92.40312052400009, "count": 90, "self": 37.61564672999634, "children": { "TorchPPOOptimizer.update": { "total": 54.787473794003745, "count": 4587, "self": 54.787473794003745 } } } } } } }, "trainer_threads": { "total": 8.900001375877764e-07, "count": 1, "self": 8.900001375877764e-07 }, "TrainerController._save_models": { "total": 0.07630845499988936, "count": 1, "self": 0.0007397249999030464, "children": { "RLTrainer._checkpoint": { "total": 0.07556872999998632, "count": 1, "self": 0.07556872999998632 } } } } } } }