{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9132003784179688, "min": 1.9104108810424805, "max": 3.295736312866211, "count": 487 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38937.453125, "min": 16330.44140625, "max": 135165.640625, "count": 487 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 73.59701492537313, "min": 41.152542372881356, "max": 999.0, "count": 487 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19724.0, "min": 12284.0, "max": 28584.0, "count": 487 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1602.9792067761405, "min": 1191.3178528921133, "max": 1614.4717205545994, "count": 476 }, "SoccerTwos.Self-play.ELO.sum": { "value": 214799.21370800282, "min": 2387.900543985528, "max": 370141.90161400626, "count": 476 }, "SoccerTwos.Step.mean": { "value": 4869986.0, "min": 9394.0, "max": 4869986.0, "count": 487 }, "SoccerTwos.Step.sum": { "value": 4869986.0, "min": 9394.0, "max": 4869986.0, "count": 487 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0037373073864728212, "min": -0.10521069169044495, "max": 0.19209492206573486, "count": 487 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.5007991790771484, "min": -17.464975357055664, "max": 30.394512176513672, "count": 487 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.009350488893687725, "min": -0.1067139282822609, "max": 0.1909307986497879, "count": 487 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.2529654502868652, "min": -17.71451187133789, "max": 30.73758316040039, "count": 487 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 487 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 487 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.06833134213490273, "min": -0.680457143556504, "max": 0.5568309854453718, "count": 487 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -9.156399846076965, "min": -43.784799695014954, "max": 60.05339992046356, "count": 487 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.06833134213490273, "min": -0.680457143556504, "max": 0.5568309854453718, "count": 487 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -9.156399846076965, "min": -43.784799695014954, "max": 60.05339992046356, "count": 487 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 487 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 487 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019839081433989728, "min": 0.011395723392100383, "max": 0.023025374176601568, "count": 234 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019839081433989728, "min": 0.011395723392100383, "max": 0.023025374176601568, "count": 234 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08724234104156495, "min": 0.0005403787494287826, "max": 0.10914969096581141, "count": 234 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08724234104156495, "min": 0.0005403787494287826, "max": 0.10914969096581141, "count": 234 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08817007541656494, "min": 0.0005422582806204445, "max": 0.11112185989816983, "count": 234 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08817007541656494, "min": 0.0005422582806204445, "max": 0.11112185989816983, "count": 234 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 234 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 234 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 234 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 234 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 234 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 234 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676646938", "python_version": "3.9.16 (main, Jan 11 2023, 16:05:54) \n[GCC 11.2.0]", "command_line_arguments": "/home/yori/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "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": "1676655969" }, "total": 9031.108888509, "count": 1, "self": 0.004375777998575359, "children": { "run_training.setup": { "total": 0.009416075999979512, "count": 1, "self": 0.009416075999979512 }, "TrainerController.start_learning": { "total": 9031.095096655, "count": 1, "self": 6.733210067630353, "children": { "TrainerController._reset_env": { "total": 3.485623283994755, "count": 25, "self": 3.485623283994755 }, "TrainerController.advance": { "total": 9020.453714380377, "count": 332290, "self": 6.471731452160384, "children": { "env_step": { "total": 7117.9216875695565, "count": 332290, "self": 5646.811411599132, "children": { "SubprocessEnvManager._take_step": { "total": 1466.4881768316327, "count": 332290, "self": 38.64869530521082, "children": { "TorchPolicy.evaluate": { "total": 1427.8394815264219, "count": 616088, "self": 1427.8394815264219 } } }, "workers": { "total": 4.622099138791782, "count": 332289, "self": 0.0, "children": { "worker_root": { "total": 9018.822043387778, "count": 332289, "is_parallel": true, "self": 4206.341205421645, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0042388199999550125, "count": 2, "is_parallel": true, "self": 0.0010232880003968603, "children": { "_process_rank_one_or_two_observation": { "total": 0.003215531999558152, "count": 8, "is_parallel": true, "self": 0.003215531999558152 } } }, "UnityEnvironment.step": { "total": 0.02563516400005028, "count": 1, "is_parallel": true, "self": 0.001190163000501343, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008680660002937657, "count": 1, "is_parallel": true, "self": 0.0008680660002937657 }, "communicator.exchange": { "total": 0.020446795999305323, "count": 1, "is_parallel": true, "self": 0.020446795999305323 }, "steps_from_proto": { "total": 0.0031301389999498497, "count": 2, "is_parallel": true, "self": 0.0006212899988895515, "children": { "_process_rank_one_or_two_observation": { "total": 0.002508849001060298, "count": 8, "is_parallel": true, "self": 0.002508849001060298 } } } } } } }, "UnityEnvironment.step": { "total": 4812.416936959127, "count": 332288, "is_parallel": true, "self": 333.3759663332703, "children": { "UnityEnvironment._generate_step_input": { "total": 209.15765872565407, "count": 332288, "is_parallel": true, "self": 209.15765872565407 }, "communicator.exchange": { "total": 3442.6407574931673, "count": 332288, "is_parallel": true, "self": 3442.6407574931673 }, "steps_from_proto": { "total": 827.2425544070356, "count": 664576, "is_parallel": true, "self": 147.6159186480536, "children": { "_process_rank_one_or_two_observation": { "total": 679.626635758982, "count": 2658304, "is_parallel": true, "self": 679.626635758982 } } } } }, "steps_from_proto": { "total": 0.06390100700537005, "count": 48, "is_parallel": true, "self": 0.011345887009156286, "children": { "_process_rank_one_or_two_observation": { "total": 0.05255511999621376, "count": 192, "is_parallel": true, "self": 0.05255511999621376 } } } } } } } } }, "trainer_advance": { "total": 1896.0602953586604, "count": 332289, "self": 54.356796848616796, "children": { "process_trajectory": { "total": 719.4373101700421, "count": 332289, "self": 715.9825304380411, "children": { "RLTrainer._checkpoint": { "total": 3.454779732001043, "count": 9, "self": 3.454779732001043 } } }, "_update_policy": { "total": 1122.2661883400015, "count": 234, "self": 690.6599851571582, "children": { "TorchPOCAOptimizer.update": { "total": 431.6062031828433, "count": 7026, "self": 431.6062031828433 } } } } } } }, "trainer_threads": { "total": 9.420000424142927e-07, "count": 1, "self": 9.420000424142927e-07 }, "TrainerController._save_models": { "total": 0.4225479809992976, "count": 1, "self": 0.001335420998657355, "children": { "RLTrainer._checkpoint": { "total": 0.4212125600006402, "count": 1, "self": 0.4212125600006402 } } } } } } }