{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8191041946411133, "min": 0.8168907165527344, "max": 2.844559669494629, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7784.76611328125, "min": 7784.76611328125, "max": 29037.265625, "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": 12.777548789978027, "min": 0.5040497183799744, "max": 12.777548789978027, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2491.6220703125, "min": 97.78564453125, "max": 2600.6904296875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06610743703683564, "min": 0.06183478732184762, "max": 0.07442297141282253, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26442974814734255, "min": 0.26442974814734255, "max": 0.3618406334015376, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19940616351132295, "min": 0.13769224339950026, "max": 0.292043315064089, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7976246540452918, "min": 0.550768973598001, "max": 1.4097946090441125, "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": 24.954545454545453, "min": 3.6136363636363638, "max": 25.29090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1098.0, "min": 159.0, "max": 1391.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.954545454545453, "min": 3.6136363636363638, "max": 25.29090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1098.0, "min": 159.0, "max": 1391.0, "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": "1784955935", "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": "1784956433" }, "total": 497.82889481999996, "count": 1, "self": 0.48564595599998484, "children": { "run_training.setup": { "total": 0.03599853000002895, "count": 1, "self": 0.03599853000002895 }, "TrainerController.start_learning": { "total": 497.30725033399995, "count": 1, "self": 0.40398559001459944, "children": { "TrainerController._reset_env": { "total": 3.6476951199999803, "count": 1, "self": 3.6476951199999803 }, "TrainerController.advance": { "total": 493.16699652698526, "count": 18192, "self": 0.41628284098885615, "children": { "env_step": { "total": 364.97144433401127, "count": 18192, "self": 286.47486634300094, "children": { "SubprocessEnvManager._take_step": { "total": 78.25181233300066, "count": 18192, "self": 1.3897810890005076, "children": { "TorchPolicy.evaluate": { "total": 76.86203124400015, "count": 18192, "self": 76.86203124400015 } } }, "workers": { "total": 0.2447656580096691, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 495.3056976140002, "count": 18192, "is_parallel": true, "self": 243.5925174019826, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005603825999969558, "count": 1, "is_parallel": true, "self": 0.004090062999921429, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015137630000481295, "count": 10, "is_parallel": true, "self": 0.0015137630000481295 } } }, "UnityEnvironment.step": { "total": 0.06093244900000627, "count": 1, "is_parallel": true, "self": 0.0006562769999618467, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039217300002292177, "count": 1, "is_parallel": true, "self": 0.00039217300002292177 }, "communicator.exchange": { "total": 0.05739015599999675, "count": 1, "is_parallel": true, "self": 0.05739015599999675 }, "steps_from_proto": { "total": 0.0024938430000247536, "count": 1, "is_parallel": true, "self": 0.0004733160000114367, "children": { "_process_rank_one_or_two_observation": { "total": 0.002020527000013317, "count": 10, "is_parallel": true, "self": 0.002020527000013317 } } } } } } }, "UnityEnvironment.step": { "total": 251.71318021201762, "count": 18191, "is_parallel": true, "self": 11.382995059004998, "children": { "UnityEnvironment._generate_step_input": { "total": 6.147279224999011, "count": 18191, "is_parallel": true, "self": 6.147279224999011 }, "communicator.exchange": { "total": 192.32144290299482, "count": 18191, "is_parallel": true, "self": 192.32144290299482 }, "steps_from_proto": { "total": 41.86146302501879, "count": 18191, "is_parallel": true, "self": 7.187498229020434, "children": { "_process_rank_one_or_two_observation": { "total": 34.67396479599836, "count": 181910, "is_parallel": true, "self": 34.67396479599836 } } } } } } } } } } }, "trainer_advance": { "total": 127.77926935198514, "count": 18192, "self": 0.4886921449796091, "children": { "process_trajectory": { "total": 26.166490241005135, "count": 18192, "self": 25.698378779004997, "children": { "RLTrainer._checkpoint": { "total": 0.4681114620001381, "count": 4, "self": 0.4681114620001381 } } }, "_update_policy": { "total": 101.12408696600039, "count": 90, "self": 41.11894161300165, "children": { "TorchPPOOptimizer.update": { "total": 60.00514535299874, "count": 4587, "self": 60.00514535299874 } } } } } } }, "trainer_threads": { "total": 1.0130002010555472e-06, "count": 1, "self": 1.0130002010555472e-06 }, "TrainerController._save_models": { "total": 0.08857208399990668, "count": 1, "self": 0.0007754709999971965, "children": { "RLTrainer._checkpoint": { "total": 0.08779661299990948, "count": 1, "self": 0.08779661299990948 } } } } } } }