{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0007812976837158, "min": 1.0007812976837158, "max": 2.856437921524048, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9555.4599609375, "min": 9555.4599609375, "max": 29284.201171875, "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": 12.424324035644531, "min": 0.36445802450180054, "max": 12.424324035644531, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2422.7431640625, "min": 70.7048568725586, "max": 2502.5966796875, "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": 0.06818129080548876, "min": 0.06365355156612007, "max": 0.07723747140456301, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27272516322195506, "min": 0.2574350411065526, "max": 0.3639823518106805, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20872818152694142, "min": 0.11903011490243909, "max": 0.2621732086089312, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8349127261077657, "min": 0.47612045960975635, "max": 1.2182807489937426, "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": 24.954545454545453, "min": 3.590909090909091, "max": 24.954545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1098.0, "min": 158.0, "max": 1334.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.954545454545453, "min": 3.590909090909091, "max": 24.954545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1098.0, "min": 158.0, "max": 1334.0, "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": "1694290933", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1694291413" }, "total": 479.39124970200004, "count": 1, "self": 0.4359011030000488, "children": { "run_training.setup": { "total": 0.04387710399998923, "count": 1, "self": 0.04387710399998923 }, "TrainerController.start_learning": { "total": 478.911471495, "count": 1, "self": 0.6146407050021025, "children": { "TrainerController._reset_env": { "total": 4.192360258000008, "count": 1, "self": 4.192360258000008 }, "TrainerController.advance": { "total": 473.96342082899787, "count": 18201, "self": 0.30940820099345956, "children": { "env_step": { "total": 473.6540126280044, "count": 18201, "self": 346.9934791769993, "children": { "SubprocessEnvManager._take_step": { "total": 126.3583015740038, "count": 18201, "self": 1.8155092190073674, "children": { "TorchPolicy.evaluate": { "total": 124.54279235499644, "count": 18201, "self": 124.54279235499644 } } }, "workers": { "total": 0.3022318770013044, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 477.4609715179991, "count": 18201, "is_parallel": true, "self": 222.00539533700777, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00577371399998583, "count": 1, "is_parallel": true, "self": 0.004310198999974091, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014635150000117392, "count": 10, "is_parallel": true, "self": 0.0014635150000117392 } } }, "UnityEnvironment.step": { "total": 0.038066950000029465, "count": 1, "is_parallel": true, "self": 0.0006334909999736738, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003205530000514045, "count": 1, "is_parallel": true, "self": 0.0003205530000514045 }, "communicator.exchange": { "total": 0.03264633500003811, "count": 1, "is_parallel": true, "self": 0.03264633500003811 }, "steps_from_proto": { "total": 0.0044665709999662795, "count": 1, "is_parallel": true, "self": 0.0004183830000101807, "children": { "_process_rank_one_or_two_observation": { "total": 0.004048187999956099, "count": 10, "is_parallel": true, "self": 0.004048187999956099 } } } } } } }, "UnityEnvironment.step": { "total": 255.45557618099133, "count": 18200, "is_parallel": true, "self": 10.693781386997443, "children": { "UnityEnvironment._generate_step_input": { "total": 5.3288747629941895, "count": 18200, "is_parallel": true, "self": 5.3288747629941895 }, "communicator.exchange": { "total": 203.4051134340043, "count": 18200, "is_parallel": true, "self": 203.4051134340043 }, "steps_from_proto": { "total": 36.02780659699539, "count": 18200, "is_parallel": true, "self": 6.701570908008534, "children": { "_process_rank_one_or_two_observation": { "total": 29.326235688986856, "count": 182000, "is_parallel": true, "self": 29.326235688986856 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001513870000735551, "count": 1, "self": 0.0001513870000735551, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 470.3923203429922, "count": 438242, "is_parallel": true, "self": 10.13793327198482, "children": { "process_trajectory": { "total": 257.7216756480073, "count": 438242, "is_parallel": true, "self": 256.53862652600725, "children": { "RLTrainer._checkpoint": { "total": 1.1830491220000567, "count": 4, "is_parallel": true, "self": 1.1830491220000567 } } }, "_update_policy": { "total": 202.53271142300008, "count": 90, "is_parallel": true, "self": 78.74189674300152, "children": { "TorchPPOOptimizer.update": { "total": 123.79081467999856, "count": 4587, "is_parallel": true, "self": 123.79081467999856 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14089831599994795, "count": 1, "self": 0.0008537499999192733, "children": { "RLTrainer._checkpoint": { "total": 0.14004456600002868, "count": 1, "self": 0.14004456600002868 } } } } } } }