{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.2742964029312134, "min": 1.2557896375656128, "max": 2.8814356327056885, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 12223.05078125, "min": 12223.05078125, "max": 29635.56640625, "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": 69.98075103759766, "min": 0.3231232762336731, "max": 69.98075103759766, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 13646.24609375, "min": 62.685916900634766, "max": 13646.24609375, "count": 20 }, "SnowballTarget.Policy.CuriosityValueEstimate.mean": { "value": 0.7933063507080078, "min": 0.5717282891273499, "max": 1.3519947528839111, "count": 20 }, "SnowballTarget.Policy.CuriosityValueEstimate.sum": { "value": 154.69473266601562, "min": 110.91529083251953, "max": 266.798583984375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06780254791516985, "min": 0.05946773661048052, "max": 0.07121647640836754, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2712101916606794, "min": 0.23787094644192208, "max": 0.35182166086651345, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.4679124100389434, "min": 0.08380453759352402, "max": 0.4679124100389434, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.8716496401557736, "min": 0.3352181503740961, "max": 1.872991480371531, "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.Losses.CuriosityForwardLoss.mean": { "value": 0.04017818967501323, "min": 0.03905368507931046, "max": 0.12323514942545444, "count": 20 }, "SnowballTarget.Losses.CuriosityForwardLoss.sum": { "value": 0.16071275870005292, "min": 0.16011890951617092, "max": 0.49294059770181775, "count": 20 }, "SnowballTarget.Losses.CuriosityInverseLoss.mean": { "value": 1.0949105261003271, "min": 1.0893409339820637, "max": 2.795914600658066, "count": 20 }, "SnowballTarget.Losses.CuriosityInverseLoss.sum": { "value": 4.3796421044013085, "min": 4.357363735928255, "max": 13.09888247415131, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 23.75, "min": 2.8863636363636362, "max": 24.09090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1045.0, "min": 127.0, "max": 1325.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.75, "min": 2.8863636363636362, "max": 24.09090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1045.0, "min": 127.0, "max": 1325.0, "count": 20 }, "SnowballTarget.Policy.CuriosityReward.mean": { "value": 8.113980094817551, "min": 8.00940542424267, "max": 13.799171115864407, "count": 20 }, "SnowballTarget.Policy.CuriosityReward.sum": { "value": 357.0151241719723, "min": 355.0877121835947, "max": 758.9544113725424, "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": "1678234603", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1678235156" }, "total": 552.3746829109999, "count": 1, "self": 0.44259460599994327, "children": { "run_training.setup": { "total": 0.1135089419999531, "count": 1, "self": 0.1135089419999531 }, "TrainerController.start_learning": { "total": 551.818579363, "count": 1, "self": 0.6335137139980134, "children": { "TrainerController._reset_env": { "total": 10.06041944499998, "count": 1, "self": 10.06041944499998 }, "TrainerController.advance": { "total": 540.9993880160022, "count": 18206, "self": 0.33940707100077816, "children": { "env_step": { "total": 540.6599809450014, "count": 18206, "self": 410.1084373199934, "children": { "SubprocessEnvManager._take_step": { "total": 130.22782587899383, "count": 18206, "self": 1.639944082985835, "children": { "TorchPolicy.evaluate": { "total": 128.587881796008, "count": 18206, "self": 32.063080668017506, "children": { "TorchPolicy.sample_actions": { "total": 96.52480112799049, "count": 18206, "self": 96.52480112799049 } } } } }, "workers": { "total": 0.3237177460141538, "count": 18206, "self": 0.0, "children": { "worker_root": { "total": 550.0193570449796, "count": 18206, "is_parallel": true, "self": 296.9998432189707, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005461514999979045, "count": 1, "is_parallel": true, "self": 0.004205272999911358, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012562420000676866, "count": 10, "is_parallel": true, "self": 0.0012562420000676866 } } }, "UnityEnvironment.step": { "total": 0.08979491100001269, "count": 1, "is_parallel": true, "self": 0.0006225370000265684, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003961229999731586, "count": 1, "is_parallel": true, "self": 0.0003961229999731586 }, "communicator.exchange": { "total": 0.08701350000001185, "count": 1, "is_parallel": true, "self": 0.08701350000001185 }, "steps_from_proto": { "total": 0.001762751000001117, "count": 1, "is_parallel": true, "self": 0.0004087729997763745, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013539780002247426, "count": 10, "is_parallel": true, "self": 0.0013539780002247426 } } } } } } }, "UnityEnvironment.step": { "total": 253.01951382600896, "count": 18205, "is_parallel": true, "self": 10.355349277020991, "children": { "UnityEnvironment._generate_step_input": { "total": 5.53136751699833, "count": 18205, "is_parallel": true, "self": 5.53136751699833 }, "communicator.exchange": { "total": 204.03382440099324, "count": 18205, "is_parallel": true, "self": 204.03382440099324 }, "steps_from_proto": { "total": 33.0989726309964, "count": 18205, "is_parallel": true, "self": 7.5520457870180735, "children": { "_process_rank_one_or_two_observation": { "total": 25.546926843978326, "count": 182050, "is_parallel": true, "self": 25.546926843978326 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015515799987042556, "count": 1, "self": 0.00015515799987042556, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 538.0169980300232, "count": 378170, "is_parallel": true, "self": 9.287811508090272, "children": { "process_trajectory": { "total": 286.67538291893163, "count": 378170, "is_parallel": true, "self": 285.87489941193144, "children": { "RLTrainer._checkpoint": { "total": 0.8004835070001945, "count": 4, "is_parallel": true, "self": 0.8004835070001945 } } }, "_update_policy": { "total": 242.05380360300126, "count": 90, "is_parallel": true, "self": 65.55533715200465, "children": { "TorchPPOOptimizer.update": { "total": 176.4984664509966, "count": 4584, "is_parallel": true, "self": 176.4984664509966 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12510302999999112, "count": 1, "self": 0.0008543960000224615, "children": { "RLTrainer._checkpoint": { "total": 0.12424863399996866, "count": 1, "self": 0.12424863399996866 } } } } } } }