{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9826010465621948, "min": 0.9826010465621948, "max": 2.8558363914489746, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9381.875, "min": 9381.875, "max": 29246.62109375, "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": 13.141436576843262, "min": 0.38063377141952515, "max": 13.141436576843262, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2562.580078125, "min": 73.84294891357422, "max": 2675.0849609375, "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": 0.0728676893383689, "min": 0.05881273066801905, "max": 0.07752699771595409, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2914707573534756, "min": 0.2352509226720762, "max": 0.36667309146301424, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1802109474060582, "min": 0.11976353093461298, "max": 0.29908440948701376, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7208437896242328, "min": 0.4790541237384519, "max": 1.453871998716803, "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": 26.045454545454547, "min": 3.3181818181818183, "max": 26.045454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1146.0, "min": 146.0, "max": 1431.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.045454545454547, "min": 3.3181818181818183, "max": 26.045454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1146.0, "min": 146.0, "max": 1431.0, "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": "1687872614", "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": "1687873093" }, "total": 478.16277968400004, "count": 1, "self": 0.43203868999989936, "children": { "run_training.setup": { "total": 0.04614060700009759, "count": 1, "self": 0.04614060700009759 }, "TrainerController.start_learning": { "total": 477.68460038700005, "count": 1, "self": 0.5576848850007536, "children": { "TrainerController._reset_env": { "total": 4.967258969999875, "count": 1, "self": 4.967258969999875 }, "TrainerController.advance": { "total": 472.0177609659993, "count": 18199, "self": 0.2672720389953156, "children": { "env_step": { "total": 471.75048892700397, "count": 18199, "self": 346.4183287970136, "children": { "SubprocessEnvManager._take_step": { "total": 125.07234579799956, "count": 18199, "self": 1.718567733015334, "children": { "TorchPolicy.evaluate": { "total": 123.35377806498423, "count": 18199, "self": 123.35377806498423 } } }, "workers": { "total": 0.2598143319908104, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 476.192144147014, "count": 18199, "is_parallel": true, "self": 224.42998876800925, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005812457000047289, "count": 1, "is_parallel": true, "self": 0.004355480999947758, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014569760000995302, "count": 10, "is_parallel": true, "self": 0.0014569760000995302 } } }, "UnityEnvironment.step": { "total": 0.07543338999994376, "count": 1, "is_parallel": true, "self": 0.0022868349999498605, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041784099994401913, "count": 1, "is_parallel": true, "self": 0.00041784099994401913 }, "communicator.exchange": { "total": 0.06709083400005511, "count": 1, "is_parallel": true, "self": 0.06709083400005511 }, "steps_from_proto": { "total": 0.005637879999994766, "count": 1, "is_parallel": true, "self": 0.0004284799999823008, "children": { "_process_rank_one_or_two_observation": { "total": 0.005209400000012465, "count": 10, "is_parallel": true, "self": 0.005209400000012465 } } } } } } }, "UnityEnvironment.step": { "total": 251.76215537900475, "count": 18198, "is_parallel": true, "self": 10.47808975801604, "children": { "UnityEnvironment._generate_step_input": { "total": 5.323175152996782, "count": 18198, "is_parallel": true, "self": 5.323175152996782 }, "communicator.exchange": { "total": 200.91563806999602, "count": 18198, "is_parallel": true, "self": 200.91563806999602 }, "steps_from_proto": { "total": 35.04525239799591, "count": 18198, "is_parallel": true, "self": 6.369510843044054, "children": { "_process_rank_one_or_two_observation": { "total": 28.675741554951856, "count": 181980, "is_parallel": true, "self": 28.675741554951856 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011615700009315333, "count": 1, "self": 0.00011615700009315333, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 468.4205160610434, "count": 447506, "is_parallel": true, "self": 9.91522848015893, "children": { "process_trajectory": { "total": 254.49092944688368, "count": 447506, "is_parallel": true, "self": 253.19412198288387, "children": { "RLTrainer._checkpoint": { "total": 1.2968074639998122, "count": 4, "is_parallel": true, "self": 1.2968074639998122 } } }, "_update_policy": { "total": 204.01435813400076, "count": 90, "is_parallel": true, "self": 81.2231268109906, "children": { "TorchPPOOptimizer.update": { "total": 122.79123132301015, "count": 4584, "is_parallel": true, "self": 122.79123132301015 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14177940900003705, "count": 1, "self": 0.0008936599999742612, "children": { "RLTrainer._checkpoint": { "total": 0.1408857490000628, "count": 1, "self": 0.1408857490000628 } } } } } } }