{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6696292161941528, "min": 0.6611582636833191, "max": 2.89028263092041, "count": 200 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6894.50244140625, "min": 6395.259765625, "max": 29583.3671875, "count": 200 }, "SnowballTarget.Step.mean": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Step.sum": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.14709186553955, "min": -0.21249984204769135, "max": 14.178264617919922, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2900.15380859375, "min": -41.22496795654297, "max": 2906.544189453125, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.98181818181818, "min": 2.7045454545454546, "max": 28.133333333333333, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1539.0, "min": 119.0, "max": 1540.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.98181818181818, "min": 2.7045454545454546, "max": 28.133333333333333, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1539.0, "min": 119.0, "max": 1540.0, "count": 200 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.028558188471167038, "min": 0.026725748635362832, "max": 0.04434683749374623, "count": 191 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.028558188471167038, "min": 0.026725748635362832, "max": 0.04434683749374623, "count": 191 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.15810729215542477, "min": 0.10300995255746538, "max": 0.31325916945934296, "count": 191 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.15810729215542477, "min": 0.10300995255746538, "max": 0.31325916945934296, "count": 191 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.844998051999851e-07, "min": 5.844998051999851e-07, "max": 0.00029836320054560004, "count": 191 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.844998051999851e-07, "min": 5.844998051999851e-07, "max": 0.00029836320054560004, "count": 191 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10019479999999999, "min": 0.10019479999999999, "max": 0.19945440000000006, "count": 191 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.10019479999999999, "min": 0.10019479999999999, "max": 0.19945440000000006, "count": 191 }, "SnowballTarget.Policy.Beta.mean": { "value": 1.9720519999999756e-05, "min": 1.9720519999999756e-05, "max": 0.0049727745600000005, "count": 191 }, "SnowballTarget.Policy.Beta.sum": { "value": 1.9720519999999756e-05, "min": 1.9720519999999756e-05, "max": 0.0049727745600000005, "count": 191 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1736256721", "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=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736261811" }, "total": 5090.106855666, "count": 1, "self": 0.5789198760003273, "children": { "run_training.setup": { "total": 0.071932462999996, "count": 1, "self": 0.071932462999996 }, "TrainerController.start_learning": { "total": 5089.456003327, "count": 1, "self": 5.914475476078223, "children": { "TrainerController._reset_env": { "total": 6.967361990999962, "count": 1, "self": 6.967361990999962 }, "TrainerController.advance": { "total": 5076.489584923923, "count": 181864, "self": 6.647302406871859, "children": { "env_step": { "total": 3782.1898319700285, "count": 181864, "self": 3217.4755047478734, "children": { "SubprocessEnvManager._take_step": { "total": 560.8338527910041, "count": 181864, "self": 18.969739925118347, "children": { "TorchPolicy.evaluate": { "total": 541.8641128658858, "count": 181864, "self": 541.8641128658858 } } }, "workers": { "total": 3.880474431150901, "count": 181864, "self": 0.0, "children": { "worker_root": { "total": 5072.342089886053, "count": 181864, "is_parallel": true, "self": 2293.352785030081, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003035667000006015, "count": 1, "is_parallel": true, "self": 0.0007426669999972546, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022930000000087603, "count": 10, "is_parallel": true, "self": 0.0022930000000087603 } } }, "UnityEnvironment.step": { "total": 0.07057284600000457, "count": 1, "is_parallel": true, "self": 0.0009292249999930391, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004906709999659142, "count": 1, "is_parallel": true, "self": 0.0004906709999659142 }, "communicator.exchange": { "total": 0.06676815500003386, "count": 1, "is_parallel": true, "self": 0.06676815500003386 }, "steps_from_proto": { "total": 0.0023847950000117635, "count": 1, "is_parallel": true, "self": 0.0004613319999862142, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019234630000255493, "count": 10, "is_parallel": true, "self": 0.0019234630000255493 } } } } } } }, "UnityEnvironment.step": { "total": 2778.989304855972, "count": 181863, "is_parallel": true, "self": 142.4343534400009, "children": { "UnityEnvironment._generate_step_input": { "total": 74.0308621319545, "count": 181863, "is_parallel": true, "self": 74.0308621319545 }, "communicator.exchange": { "total": 2148.1917395409873, "count": 181863, "is_parallel": true, "self": 2148.1917395409873 }, "steps_from_proto": { "total": 414.3323497430292, "count": 181863, "is_parallel": true, "self": 78.15416531693825, "children": { "_process_rank_one_or_two_observation": { "total": 336.178184426091, "count": 1818630, "is_parallel": true, "self": 336.178184426091 } } } } } } } } } } }, "trainer_advance": { "total": 1287.6524505470227, "count": 181864, "self": 7.417523052091838, "children": { "process_trajectory": { "total": 310.54778576793166, "count": 181864, "self": 306.7813990899297, "children": { "RLTrainer._checkpoint": { "total": 3.766386678001936, "count": 40, "self": 3.766386678001936 } } }, "_update_policy": { "total": 969.6871417269992, "count": 191, "self": 529.7730874569855, "children": { "TorchPPOOptimizer.update": { "total": 439.9140542700137, "count": 11604, "self": 439.9140542700137 } } } } } } }, "trainer_threads": { "total": 1.1829997674794868e-06, "count": 1, "self": 1.1829997674794868e-06 }, "TrainerController._save_models": { "total": 0.08457975299916143, "count": 1, "self": 0.0012809339987143176, "children": { "RLTrainer._checkpoint": { "total": 0.08329881900044711, "count": 1, "self": 0.08329881900044711 } } } } } } }