{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9954781532287598, "min": 0.9954781532287598, "max": 2.8717830181121826, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9614.328125, "min": 9614.328125, "max": 29567.87890625, "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": 12.850738525390625, "min": 0.2479480803012848, "max": 12.850738525390625, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2505.89404296875, "min": 48.1019287109375, "max": 2614.611328125, "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": 0.06448418590754919, "min": 0.06448418590754919, "max": 0.07634707675406746, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25793674363019675, "min": 0.25793674363019675, "max": 0.36602303773100836, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21522666915666824, "min": 0.12340885898961193, "max": 0.2769523937328189, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.860906676626673, "min": 0.4936354359584477, "max": 1.3847619686640944, "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": 25.25, "min": 3.159090909090909, "max": 25.25, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1111.0, "min": 139.0, "max": 1387.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.25, "min": 3.159090909090909, "max": 25.25, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1111.0, "min": 139.0, "max": 1387.0, "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": "1678620009", "python_version": "3.9.1 (default, Dec 11 2020, 14:32:07) \n[GCC 7.3.0]", "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": "1.22.3", "end_time_seconds": "1678620763" }, "total": 753.968048056, "count": 1, "self": 0.5501043260003371, "children": { "run_training.setup": { "total": 0.0643799559998115, "count": 1, "self": 0.0643799559998115 }, "TrainerController.start_learning": { "total": 753.3535637739999, "count": 1, "self": 1.0607788920217445, "children": { "TrainerController._reset_env": { "total": 0.8501221300000452, "count": 1, "self": 0.8501221300000452 }, "TrainerController.advance": { "total": 751.2900184189782, "count": 18211, "self": 0.5246234429816923, "children": { "env_step": { "total": 750.7653949759965, "count": 18211, "self": 623.1554590739947, "children": { "SubprocessEnvManager._take_step": { "total": 127.09017438801766, "count": 18211, "self": 2.6503032510256617, "children": { "TorchPolicy.evaluate": { "total": 124.439871136992, "count": 18211, "self": 21.393642663983428, "children": { "TorchPolicy.sample_actions": { "total": 103.04622847300857, "count": 18211, "self": 103.04622847300857 } } } } }, "workers": { "total": 0.5197615139841218, "count": 18211, "self": 0.0, "children": { "worker_root": { "total": 750.1146009259962, "count": 18211, "is_parallel": true, "self": 334.8344122139754, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003095978999908766, "count": 1, "is_parallel": true, "self": 0.001053733999697215, "children": { "_process_rank_one_or_two_observation": { "total": 0.002042245000211551, "count": 10, "is_parallel": true, "self": 0.002042245000211551 } } }, "UnityEnvironment.step": { "total": 0.05117417400015256, "count": 1, "is_parallel": true, "self": 0.0007775529998070851, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046302500004458125, "count": 1, "is_parallel": true, "self": 0.00046302500004458125 }, "communicator.exchange": { "total": 0.04727880600012213, "count": 1, "is_parallel": true, "self": 0.04727880600012213 }, "steps_from_proto": { "total": 0.002654790000178764, "count": 1, "is_parallel": true, "self": 0.0006044660001407465, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020503240000380174, "count": 10, "is_parallel": true, "self": 0.0020503240000380174 } } } } } } }, "UnityEnvironment.step": { "total": 415.28018871202084, "count": 18210, "is_parallel": true, "self": 15.521902754031316, "children": { "UnityEnvironment._generate_step_input": { "total": 8.298703827997997, "count": 18210, "is_parallel": true, "self": 8.298703827997997 }, "communicator.exchange": { "total": 335.30951119898896, "count": 18210, "is_parallel": true, "self": 335.30951119898896 }, "steps_from_proto": { "total": 56.150070931002574, "count": 18210, "is_parallel": true, "self": 13.114688375027754, "children": { "_process_rank_one_or_two_observation": { "total": 43.03538255597482, "count": 182100, "is_parallel": true, "self": 43.03538255597482 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017403099991497584, "count": 1, "self": 0.00017403099991497584, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 744.7252130650568, "count": 647572, "is_parallel": true, "self": 18.775923434906872, "children": { "process_trajectory": { "total": 397.75672589714964, "count": 647572, "is_parallel": true, "self": 395.38635570814927, "children": { "RLTrainer._checkpoint": { "total": 2.3703701890003686, "count": 4, "is_parallel": true, "self": 2.3703701890003686 } } }, "_update_policy": { "total": 328.19256373300027, "count": 90, "is_parallel": true, "self": 153.47255650400007, "children": { "TorchPPOOptimizer.update": { "total": 174.7200072290002, "count": 4587, "is_parallel": true, "self": 174.7200072290002 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15247030199998335, "count": 1, "self": 0.0010361050001392869, "children": { "RLTrainer._checkpoint": { "total": 0.15143419699984406, "count": 1, "self": 0.15143419699984406 } } } } } } }