{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.045432209968567, "min": 1.0299731492996216, "max": 2.8638088703155518, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10004.7861328125, "min": 10004.7861328125, "max": 29422.7734375, "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": 12.798412322998047, "min": 0.4742192029953003, "max": 12.798412322998047, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2495.6904296875, "min": 91.99852752685547, "max": 2579.38037109375, "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": 0.06948003139547711, "min": 0.062459912279354844, "max": 0.07626449381481792, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27792012558190843, "min": 0.24983964911741938, "max": 0.36440458511574164, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22868668865047248, "min": 0.14512717366154654, "max": 0.3195142649552401, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9147467546018899, "min": 0.5805086946461862, "max": 1.417581895110654, "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": 25.045454545454547, "min": 4.159090909090909, "max": 25.509090909090908, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1102.0, "min": 183.0, "max": 1403.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.045454545454547, "min": 4.159090909090909, "max": 25.509090909090908, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1102.0, "min": 183.0, "max": 1403.0, "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": "1686449857", "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": "1686450305" }, "total": 447.3857608909999, "count": 1, "self": 0.4339539519999107, "children": { "run_training.setup": { "total": 0.04469067399998039, "count": 1, "self": 0.04469067399998039 }, "TrainerController.start_learning": { "total": 446.907116265, "count": 1, "self": 0.5177499269912005, "children": { "TrainerController._reset_env": { "total": 3.932370287000026, "count": 1, "self": 3.932370287000026 }, "TrainerController.advance": { "total": 442.3224597790087, "count": 18204, "self": 0.24182840401408612, "children": { "env_step": { "total": 442.0806313749946, "count": 18204, "self": 322.7095772129942, "children": { "SubprocessEnvManager._take_step": { "total": 119.12302287100385, "count": 18204, "self": 1.8725385380009811, "children": { "TorchPolicy.evaluate": { "total": 117.25048433300287, "count": 18204, "self": 117.25048433300287 } } }, "workers": { "total": 0.24803129099655052, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 445.4627410200027, "count": 18204, "is_parallel": true, "self": 211.41679359901116, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004782204999969508, "count": 1, "is_parallel": true, "self": 0.003447568000069623, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013346369998998853, "count": 10, "is_parallel": true, "self": 0.0013346369998998853 } } }, "UnityEnvironment.step": { "total": 0.0575475360000155, "count": 1, "is_parallel": true, "self": 0.0006273099999134502, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034690300003603625, "count": 1, "is_parallel": true, "self": 0.00034690300003603625 }, "communicator.exchange": { "total": 0.05220101700001578, "count": 1, "is_parallel": true, "self": 0.05220101700001578 }, "steps_from_proto": { "total": 0.00437230600005023, "count": 1, "is_parallel": true, "self": 0.0004112130000066827, "children": { "_process_rank_one_or_two_observation": { "total": 0.003961093000043547, "count": 10, "is_parallel": true, "self": 0.003961093000043547 } } } } } } }, "UnityEnvironment.step": { "total": 234.04594742099152, "count": 18203, "is_parallel": true, "self": 9.238749782982723, "children": { "UnityEnvironment._generate_step_input": { "total": 5.081706666011087, "count": 18203, "is_parallel": true, "self": 5.081706666011087 }, "communicator.exchange": { "total": 188.34066325600315, "count": 18203, "is_parallel": true, "self": 188.34066325600315 }, "steps_from_proto": { "total": 31.38482771599456, "count": 18203, "is_parallel": true, "self": 5.799367432033705, "children": { "_process_rank_one_or_two_observation": { "total": 25.585460283960856, "count": 182030, "is_parallel": true, "self": 25.585460283960856 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012091000007785624, "count": 1, "self": 0.00012091000007785624, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 439.00430560805876, "count": 418402, "is_parallel": true, "self": 9.048191519006423, "children": { "process_trajectory": { "total": 240.0224665970518, "count": 418402, "is_parallel": true, "self": 238.4243323510516, "children": { "RLTrainer._checkpoint": { "total": 1.5981342460001997, "count": 4, "is_parallel": true, "self": 1.5981342460001997 } } }, "_update_policy": { "total": 189.93364749200055, "count": 90, "is_parallel": true, "self": 74.90021306800952, "children": { "TorchPPOOptimizer.update": { "total": 115.03343442399103, "count": 4587, "is_parallel": true, "self": 115.03343442399103 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13441536200002702, "count": 1, "self": 0.0008091729998795927, "children": { "RLTrainer._checkpoint": { "total": 0.13360618900014742, "count": 1, "self": 0.13360618900014742 } } } } } } }