{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.328736662864685, "min": 1.328736662864685, "max": 2.843930244445801, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 12745.2421875, "min": 12745.2421875, "max": 29155.97265625, "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": 10.486564636230469, "min": 0.6738138198852539, "max": 10.486564636230469, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2044.880126953125, "min": 130.71987915039062, "max": 2113.83740234375, "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": 0.06711503298076932, "min": 0.06711503298076932, "max": 0.07077088265608494, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26846013192307727, "min": 0.26846013192307727, "max": 0.35302607349228576, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.4697324723969487, "min": 0.20209949606262587, "max": 0.6343104608707568, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.8789298895877948, "min": 0.8083979842505035, "max": 2.807723384008688, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.6940973060000016e-06, "min": 2.6940973060000016e-06, "max": 9.7294002706e-05, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.0776389224000007e-05, "min": 1.0776389224000007e-05, "max": 0.00046172003828000004, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.197294, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.9617200000000001, "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": 20.977272727272727, "min": 3.4318181818181817, "max": 20.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 923.0, "min": 151.0, "max": 1117.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 20.977272727272727, "min": 3.4318181818181817, "max": 20.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 923.0, "min": 151.0, "max": 1117.0, "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": "1691066365", "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": "1691069571" }, "total": 3206.096668877, "count": 1, "self": 0.3277779059999375, "children": { "run_training.setup": { "total": 0.03954434500002435, "count": 1, "self": 0.03954434500002435 }, "TrainerController.start_learning": { "total": 3205.729346626, "count": 1, "self": 0.5994457930105455, "children": { "TrainerController._reset_env": { "total": 4.406403759, "count": 1, "self": 4.406403759 }, "TrainerController.advance": { "total": 3200.583467309989, "count": 18206, "self": 0.2968629349506955, "children": { "env_step": { "total": 3200.286604375038, "count": 18206, "self": 3085.39401313201, "children": { "SubprocessEnvManager._take_step": { "total": 114.60609719801238, "count": 18206, "self": 1.6318862410024053, "children": { "TorchPolicy.evaluate": { "total": 112.97421095700997, "count": 18206, "self": 112.97421095700997 } } }, "workers": { "total": 0.286494045015786, "count": 18206, "self": 0.0, "children": { "worker_root": { "total": 3204.8633939049823, "count": 18206, "is_parallel": true, "self": 2999.4370102329985, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002146621999997933, "count": 1, "is_parallel": true, "self": 0.0006777509999551512, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014688710000427818, "count": 10, "is_parallel": true, "self": 0.0014688710000427818 } } }, "UnityEnvironment.step": { "total": 0.03452292699995496, "count": 1, "is_parallel": true, "self": 0.0003943349999531165, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002990620000105082, "count": 1, "is_parallel": true, "self": 0.0002990620000105082 }, "communicator.exchange": { "total": 0.03246124700001474, "count": 1, "is_parallel": true, "self": 0.03246124700001474 }, "steps_from_proto": { "total": 0.0013682829999766, "count": 1, "is_parallel": true, "self": 0.00027836800001068696, "children": { "_process_rank_one_or_two_observation": { "total": 0.001089914999965913, "count": 10, "is_parallel": true, "self": 0.001089914999965913 } } } } } } }, "UnityEnvironment.step": { "total": 205.42638367198396, "count": 18205, "is_parallel": true, "self": 9.86256634791664, "children": { "UnityEnvironment._generate_step_input": { "total": 5.116454900025303, "count": 18205, "is_parallel": true, "self": 5.116454900025303 }, "communicator.exchange": { "total": 158.56935838501863, "count": 18205, "is_parallel": true, "self": 158.56935838501863 }, "steps_from_proto": { "total": 31.87800403902338, "count": 18205, "is_parallel": true, "self": 5.723444310003231, "children": { "_process_rank_one_or_two_observation": { "total": 26.15455972902015, "count": 182050, "is_parallel": true, "self": 26.15455972902015 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017297800013693632, "count": 1, "self": 0.00017297800013693632, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 3199.095331037006, "count": 233500, "is_parallel": true, "self": 5.117404167977838, "children": { "process_trajectory": { "total": 225.13145889102452, "count": 233500, "is_parallel": true, "self": 224.28792106302467, "children": { "RLTrainer._checkpoint": { "total": 0.8435378279998531, "count": 4, "is_parallel": true, "self": 0.8435378279998531 } } }, "_update_policy": { "total": 2968.8464679780036, "count": 90, "is_parallel": true, "self": 1533.1906700190361, "children": { "TorchPPOOptimizer.update": { "total": 1435.6557979589675, "count": 152900, "is_parallel": true, "self": 1435.6557979589675 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13985678600010942, "count": 1, "self": 0.0008848030001900042, "children": { "RLTrainer._checkpoint": { "total": 0.13897198299991942, "count": 1, "self": 0.13897198299991942 } } } } } } }