{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6835042238235474, "min": 1.6298682689666748, "max": 3.295746326446533, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34585.91015625, "min": 19631.7421875, "max": 133274.546875, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 51.28865979381443, "min": 44.125, "max": 999.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19900.0, "min": 10096.0, "max": 30088.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1590.337186045874, "min": 1193.495605072833, "max": 1639.6240175019714, "count": 973 }, "SoccerTwos.Self-play.ELO.sum": { "value": 308525.41409289953, "min": 2387.9309023650144, "max": 356115.70514374506, "count": 973 }, "SoccerTwos.Step.mean": { "value": 9999950.0, "min": 9918.0, "max": 9999950.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 9999950.0, "min": 9918.0, "max": 9999950.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.04747204855084419, "min": -0.1485600620508194, "max": 0.16338199377059937, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 9.162105560302734, "min": -25.700889587402344, "max": 26.565298080444336, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.04477151110768318, "min": -0.14526383578777313, "max": 0.1668882668018341, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 8.640901565551758, "min": -25.130643844604492, "max": 27.05544090270996, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.07125388649461183, "min": -0.5714285714285714, "max": 0.44592727774923496, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 13.752000093460083, "min": -56.70379960536957, "max": 60.203800439834595, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.07125388649461183, "min": -0.5714285714285714, "max": 0.44592727774923496, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 13.752000093460083, "min": -56.70379960536957, "max": 60.203800439834595, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.020147728574617454, "min": 0.010620777231209407, "max": 0.02348307948753548, "count": 482 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.020147728574617454, "min": 0.010620777231209407, "max": 0.02348307948753548, "count": 482 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1045210654536883, "min": 3.9221887467040995e-06, "max": 0.12136046414573988, "count": 482 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1045210654536883, "min": 3.9221887467040995e-06, "max": 0.12136046414573988, "count": 482 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10551010196407636, "min": 3.8932328910353435e-06, "max": 0.1243433194855849, "count": 482 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10551010196407636, "min": 3.8932328910353435e-06, "max": 0.1243433194855849, "count": 482 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 482 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 482 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 482 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 482 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 482 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 482 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694239828", "python_version": "3.10.6 (main, Aug 10 2022, 05:05:41) [GCC 9.4.0]", "command_line_arguments": "/home/cogstack/.pyenv/versions/3.10.6/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": "1694266971" }, "total": 27142.885829193052, "count": 1, "self": 0.3233174770139158, "children": { "run_training.setup": { "total": 0.02085940702818334, "count": 1, "self": 0.02085940702818334 }, "TrainerController.start_learning": { "total": 27142.54165230901, "count": 1, "self": 20.760503608733416, "children": { "TrainerController._reset_env": { "total": 5.5956537919119, "count": 50, "self": 5.5956537919119 }, "TrainerController.advance": { "total": 27115.92019592831, "count": 684299, "self": 20.890359795303084, "children": { "env_step": { "total": 20321.38538823859, "count": 684299, "self": 14906.691656839685, "children": { "SubprocessEnvManager._take_step": { "total": 5402.722578252549, "count": 684299, "self": 149.27927884238306, "children": { "TorchPolicy.evaluate": { "total": 5253.443299410166, "count": 1260924, "self": 5253.443299410166 } } }, "workers": { "total": 11.971153146354482, "count": 684299, "self": 0.0, "children": { "worker_root": { "total": 27103.916117504938, "count": 684299, "is_parallel": true, "self": 14862.88808951911, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002989628934301436, "count": 2, "is_parallel": true, "self": 0.0007436459418386221, "children": { "_process_rank_one_or_two_observation": { "total": 0.002245982992462814, "count": 8, "is_parallel": true, "self": 0.002245982992462814 } } }, "UnityEnvironment.step": { "total": 0.037883343058638275, "count": 1, "is_parallel": true, "self": 0.0018339292146265507, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009027869673445821, "count": 1, "is_parallel": true, "self": 0.0009027869673445821 }, "communicator.exchange": { "total": 0.029121760977432132, "count": 1, "is_parallel": true, "self": 0.029121760977432132 }, "steps_from_proto": { "total": 0.00602486589923501, "count": 2, "is_parallel": true, "self": 0.0012357208179309964, "children": { "_process_rank_one_or_two_observation": { "total": 0.004789145081304014, "count": 8, "is_parallel": true, "self": 0.004789145081304014 } } } } } } }, "UnityEnvironment.step": { "total": 12240.826549586141, "count": 684298, "is_parallel": true, "self": 808.3874955732608, "children": { "UnityEnvironment._generate_step_input": { "total": 472.7278697233414, "count": 684298, "is_parallel": true, "self": 472.7278697233414 }, "communicator.exchange": { "total": 8373.162975011859, "count": 684298, "is_parallel": true, "self": 8373.162975011859 }, "steps_from_proto": { "total": 2586.54820927768, "count": 1368596, "is_parallel": true, "self": 512.5392411110224, "children": { "_process_rank_one_or_two_observation": { "total": 2074.0089681666577, "count": 5474384, "is_parallel": true, "self": 2074.0089681666577 } } } } }, "steps_from_proto": { "total": 0.201478399685584, "count": 98, "is_parallel": true, "self": 0.03929394809529185, "children": { "_process_rank_one_or_two_observation": { "total": 0.16218445159029216, "count": 392, "is_parallel": true, "self": 0.16218445159029216 } } } } } } } } }, "trainer_advance": { "total": 6773.644447894418, "count": 684299, "self": 145.80233383376617, "children": { "process_trajectory": { "total": 2434.7693534394493, "count": 684299, "self": 2429.4081286871806, "children": { "RLTrainer._checkpoint": { "total": 5.361224752268754, "count": 20, "self": 5.361224752268754 } } }, "_update_policy": { "total": 4193.072760621202, "count": 482, "self": 2277.206096544978, "children": { "TorchPOCAOptimizer.update": { "total": 1915.866664076224, "count": 14463, "self": 1915.866664076224 } } } } } } }, "trainer_threads": { "total": 1.2529781088232994e-06, "count": 1, "self": 1.2529781088232994e-06 }, "TrainerController._save_models": { "total": 0.26529772707726806, "count": 1, "self": 0.0028997660847380757, "children": { "RLTrainer._checkpoint": { "total": 0.26239796099253, "count": 1, "self": 0.26239796099253 } } } } } } }