{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1191916465759277, "min": 1.1191916465759277, "max": 2.8531391620635986, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10698.3525390625, "min": 10698.3525390625, "max": 29218.998046875, "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": 12.033623695373535, "min": 0.4064042270183563, "max": 12.033623695373535, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2346.556640625, "min": 78.84242248535156, "max": 2430.198486328125, "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": 0.07003515125046866, "min": 0.06264512891990735, "max": 0.0734945674540701, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28014060500187465, "min": 0.2577303381175643, "max": 0.36541422807603535, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23823237550609253, "min": 0.11615201118561969, "max": 0.26493121325677516, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9529295020243701, "min": 0.46460804474247874, "max": 1.2892846278115815, "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": 23.522727272727273, "min": 3.1363636363636362, "max": 23.78181818181818, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1035.0, "min": 138.0, "max": 1308.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.522727272727273, "min": 3.1363636363636362, "max": 23.78181818181818, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1035.0, "min": 138.0, "max": 1308.0, "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": "1687283931", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "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": "1687284412" }, "total": 481.092542527, "count": 1, "self": 0.43581991599990033, "children": { "run_training.setup": { "total": 0.0429973059999611, "count": 1, "self": 0.0429973059999611 }, "TrainerController.start_learning": { "total": 480.6137253050001, "count": 1, "self": 0.5377170259945387, "children": { "TrainerController._reset_env": { "total": 5.488350195000066, "count": 1, "self": 5.488350195000066 }, "TrainerController.advance": { "total": 474.4429861560053, "count": 18202, "self": 0.2579624040060935, "children": { "env_step": { "total": 474.1850237519992, "count": 18202, "self": 343.35884145098396, "children": { "SubprocessEnvManager._take_step": { "total": 130.55850385702058, "count": 18202, "self": 1.8053591750210671, "children": { "TorchPolicy.evaluate": { "total": 128.75314468199952, "count": 18202, "self": 128.75314468199952 } } }, "workers": { "total": 0.26767844399466867, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 478.9257982649907, "count": 18202, "is_parallel": true, "self": 225.33555810697737, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006991418999973575, "count": 1, "is_parallel": true, "self": 0.004580183999905785, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024112350000677907, "count": 10, "is_parallel": true, "self": 0.0024112350000677907 } } }, "UnityEnvironment.step": { "total": 0.03767872299999908, "count": 1, "is_parallel": true, "self": 0.0006520340000406577, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000397464000002401, "count": 1, "is_parallel": true, "self": 0.000397464000002401 }, "communicator.exchange": { "total": 0.03436134699995819, "count": 1, "is_parallel": true, "self": 0.03436134699995819 }, "steps_from_proto": { "total": 0.002267877999997836, "count": 1, "is_parallel": true, "self": 0.0004303549999349343, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018375230000629017, "count": 10, "is_parallel": true, "self": 0.0018375230000629017 } } } } } } }, "UnityEnvironment.step": { "total": 253.59024015801333, "count": 18201, "is_parallel": true, "self": 10.768139357012615, "children": { "UnityEnvironment._generate_step_input": { "total": 5.608138158996894, "count": 18201, "is_parallel": true, "self": 5.608138158996894 }, "communicator.exchange": { "total": 200.24623678701005, "count": 18201, "is_parallel": true, "self": 200.24623678701005 }, "steps_from_proto": { "total": 36.96772585499377, "count": 18201, "is_parallel": true, "self": 6.731853036971984, "children": { "_process_rank_one_or_two_observation": { "total": 30.23587281802179, "count": 182010, "is_parallel": true, "self": 30.23587281802179 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001582170000347105, "count": 1, "self": 0.0001582170000347105, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 470.75962647896233, "count": 456110, "is_parallel": true, "self": 10.02948351297232, "children": { "process_trajectory": { "total": 259.9265111049905, "count": 456110, "is_parallel": true, "self": 258.95338929299055, "children": { "RLTrainer._checkpoint": { "total": 0.9731218119999312, "count": 4, "is_parallel": true, "self": 0.9731218119999312 } } }, "_update_policy": { "total": 200.80363186099953, "count": 90, "is_parallel": true, "self": 77.3990473780068, "children": { "TorchPPOOptimizer.update": { "total": 123.40458448299273, "count": 4587, "is_parallel": true, "self": 123.40458448299273 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1445137110001724, "count": 1, "self": 0.0008494560001963691, "children": { "RLTrainer._checkpoint": { "total": 0.14366425499997604, "count": 1, "self": 0.14366425499997604 } } } } } } }