{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3697651624679565, "min": 1.2648961544036865, "max": 3.2957470417022705, "count": 2893 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27044.64453125, "min": 22575.865234375, "max": 118413.796875, "count": 2893 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 63.52564102564103, "min": 33.55172413793103, "max": 999.0, "count": 2893 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19820.0, "min": 14452.0, "max": 27484.0, "count": 2893 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1659.8433784207673, "min": 1197.9671043715189, "max": 1716.153060176751, "count": 2891 }, "SoccerTwos.Self-play.ELO.sum": { "value": 258935.5670336397, "min": 2408.6515307437826, "max": 446570.9739819133, "count": 2891 }, "SoccerTwos.Step.mean": { "value": 28929950.0, "min": 9758.0, "max": 28929950.0, "count": 2893 }, "SoccerTwos.Step.sum": { "value": 28929950.0, "min": 9758.0, "max": 28929950.0, "count": 2893 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.004980441648513079, "min": -0.13963189721107483, "max": 0.23325316607952118, "count": 2893 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.7719684839248657, "min": -25.831899642944336, "max": 33.355201721191406, "count": 2893 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0066825589165091515, "min": -0.14365743100643158, "max": 0.24196134507656097, "count": 2893 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.0357966423034668, "min": -26.57662582397461, "max": 34.60047149658203, "count": 2893 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2893 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2893 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.04979354643052624, "min": -0.6910166690746943, "max": 0.42671578808834676, "count": 2893 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -7.717999696731567, "min": -84.68740034103394, "max": 54.21119982004166, "count": 2893 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.04979354643052624, "min": -0.6910166690746943, "max": 0.42671578808834676, "count": 2893 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -7.717999696731567, "min": -84.68740034103394, "max": 54.21119982004166, "count": 2893 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2893 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2893 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01574349036285033, "min": 0.009663422273782392, "max": 0.026608878828119485, "count": 1403 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01574349036285033, "min": 0.009663422273782392, "max": 0.026608878828119485, "count": 1403 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09998235156138738, "min": 0.000996815184286485, "max": 0.1347443292538325, "count": 1403 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09998235156138738, "min": 0.000996815184286485, "max": 0.1347443292538325, "count": 1403 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10118135089675585, "min": 0.0010012711369199677, "max": 0.13781699165701866, "count": 1403 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10118135089675585, "min": 0.0010012711369199677, "max": 0.13781699165701866, "count": 1403 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1403 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1403 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1403 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1403 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1403 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1403 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682410090", "python_version": "3.9.16 (main, Mar 8 2023, 04:29:44) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/shahoorkausmally/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.app --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", "numpy_version": "1.21.2", "end_time_seconds": "1682587958" }, "total": 177877.038014227, "count": 1, "self": 0.009543682012008503, "children": { "run_training.setup": { "total": 0.037134902000000025, "count": 1, "self": 0.037134902000000025 }, "TrainerController.start_learning": { "total": 177876.991335643, "count": 1, "self": 46.906998191348976, "children": { "TrainerController._reset_env": { "total": 6.980836843951093, "count": 145, "self": 6.980836843951093 }, "TrainerController.advance": { "total": 177822.6658479777, "count": 2016088, "self": 46.45848843094427, "children": { "env_step": { "total": 44195.718673491014, "count": 2016088, "self": 34837.5042717071, "children": { "SubprocessEnvManager._take_step": { "total": 9326.21591820184, "count": 2016088, "self": 277.45708925111103, "children": { "TorchPolicy.evaluate": { "total": 9048.75882895073, "count": 3634190, "self": 9048.75882895073 } } }, "workers": { "total": 31.99848358207666, "count": 2016088, "self": 0.0, "children": { "worker_root": { "total": 177759.29820163586, "count": 2016088, "is_parallel": true, "self": 149860.4279496555, "children": { "steps_from_proto": { "total": 0.35539504585845405, "count": 290, "is_parallel": true, "self": 0.0852955782905771, "children": { "_process_rank_one_or_two_observation": { "total": 0.27009946756787695, "count": 1160, "is_parallel": true, "self": 0.27009946756787695 } } }, "UnityEnvironment.step": { "total": 27898.51485693449, "count": 2016088, "is_parallel": true, "self": 1757.6433416013751, "children": { "UnityEnvironment._generate_step_input": { "total": 1385.140794365653, "count": 2016088, "is_parallel": true, "self": 1385.140794365653 }, "communicator.exchange": { "total": 20200.67506038736, "count": 2016088, "is_parallel": true, "self": 20200.67506038736 }, "steps_from_proto": { "total": 4555.055660580105, "count": 4032176, "is_parallel": true, "self": 1111.0086384964243, "children": { "_process_rank_one_or_two_observation": { "total": 3444.0470220836805, "count": 16128704, "is_parallel": true, "self": 3444.0470220836805 } } } } } } } } } } }, "trainer_advance": { "total": 133580.48868605576, "count": 2016088, "self": 353.2625176515721, "children": { "process_trajectory": { "total": 19580.932550105896, "count": 2016088, "self": 19565.2294530829, "children": { "RLTrainer._checkpoint": { "total": 15.703097022997099, "count": 57, "self": 15.703097022997099 } } }, "_update_policy": { "total": 113646.2936182983, "count": 1404, "self": 6876.812801696331, "children": { "TorchPOCAOptimizer.update": { "total": 106769.48081660196, "count": 42092, "self": 106769.48081660196 } } } } } } }, "trainer_threads": { "total": 1.6659905668348074e-06, "count": 1, "self": 1.6659905668348074e-06 }, "TrainerController._save_models": { "total": 0.437650963984197, "count": 1, "self": 0.002921929000876844, "children": { "RLTrainer._checkpoint": { "total": 0.43472903498332016, "count": 1, "self": 0.43472903498332016 } } } } } } }