{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9007693529129028, "min": 1.8985053300857544, "max": 3.295764207839966, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37528.7890625, "min": 27137.630859375, "max": 124863.2890625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 51.229166666666664, "min": 40.51239669421488, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19672.0, "min": 14176.0, "max": 28236.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1544.5808485474847, "min": 1190.9908670829782, "max": 1562.3011955270338, "count": 447 }, "SoccerTwos.Self-play.ELO.sum": { "value": 296559.5229211171, "min": 2382.523960205788, "max": 356043.1525078966, "count": 447 }, "SoccerTwos.Step.mean": { "value": 4999964.0, "min": 9134.0, "max": 4999964.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999964.0, "min": 9134.0, "max": 4999964.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0005910669569857419, "min": -0.10813776403665543, "max": 0.160194993019104, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.11348485946655273, "min": -16.919414520263672, "max": 26.432172775268555, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0011572042712941766, "min": -0.10860361158847809, "max": 0.16118696331977844, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.2221832275390625, "min": -17.170551300048828, "max": 26.595849990844727, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0339020856966575, "min": -0.5454545454545454, "max": 0.44335999886194866, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 6.50920045375824, "min": -40.44259983301163, "max": 52.48079997301102, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0339020856966575, "min": -0.5454545454545454, "max": 0.44335999886194866, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 6.50920045375824, "min": -40.44259983301163, "max": 52.48079997301102, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01989491223357618, "min": 0.011979770788457245, "max": 0.024236690984980668, "count": 238 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01989491223357618, "min": 0.011979770788457245, "max": 0.024236690984980668, "count": 238 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1158855177462101, "min": 4.5519653824044326e-08, "max": 0.1158855177462101, "count": 238 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1158855177462101, "min": 4.5519653824044326e-08, "max": 0.1158855177462101, "count": 238 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11915981372197469, "min": 9.39508446151649e-08, "max": 0.11915981372197469, "count": 238 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11915981372197469, "min": 9.39508446151649e-08, "max": 0.11915981372197469, "count": 238 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 238 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 238 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 238 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 238 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 238 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 238 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676133082", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\schwese\\.conda\\envs\\RL\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1676148898" }, "total": 15816.1301487, "count": 1, "self": 0.30383230000006733, "children": { "run_training.setup": { "total": 0.09467429999999988, "count": 1, "self": 0.09467429999999988 }, "TrainerController.start_learning": { "total": 15815.7316421, "count": 1, "self": 8.988539599677097, "children": { "TrainerController._reset_env": { "total": 4.854592599995241, "count": 25, "self": 4.854592599995241 }, "TrainerController.advance": { "total": 15801.74241040033, "count": 337781, "self": 8.923450500253239, "children": { "env_step": { "total": 6184.148542200114, "count": 337781, "self": 4799.395221399835, "children": { "SubprocessEnvManager._take_step": { "total": 1378.8780880997258, "count": 337781, "self": 46.866440399311614, "children": { "TorchPolicy.evaluate": { "total": 1332.0116477004142, "count": 633306, "self": 1332.0116477004142 } } }, "workers": { "total": 5.875232700553685, "count": 337781, "self": 0.0, "children": { "worker_root": { "total": 15799.158080900217, "count": 337781, "is_parallel": true, "self": 11947.830452900516, "children": { "steps_from_proto": { "total": 0.04382719999838791, "count": 50, "is_parallel": true, "self": 0.009136500000816117, "children": { "_process_rank_one_or_two_observation": { "total": 0.034690699997571794, "count": 200, "is_parallel": true, "self": 0.034690699997571794 } } }, "UnityEnvironment.step": { "total": 3851.283800799703, "count": 337781, "is_parallel": true, "self": 199.03164479947327, "children": { "UnityEnvironment._generate_step_input": { "total": 165.05185690036524, "count": 337781, "is_parallel": true, "self": 165.05185690036524 }, "communicator.exchange": { "total": 2892.3608176995854, "count": 337781, "is_parallel": true, "self": 2892.3608176995854 }, "steps_from_proto": { "total": 594.8394814002789, "count": 675562, "is_parallel": true, "self": 121.9542823003182, "children": { "_process_rank_one_or_two_observation": { "total": 472.88519909996074, "count": 2702248, "is_parallel": true, "self": 472.88519909996074 } } } } } } } } } } }, "trainer_advance": { "total": 9608.670417699961, "count": 337781, "self": 64.86049049960639, "children": { "process_trajectory": { "total": 1327.2437884003425, "count": 337781, "self": 1325.8188255003429, "children": { "RLTrainer._checkpoint": { "total": 1.4249628999996276, "count": 10, "self": 1.4249628999996276 } } }, "_update_policy": { "total": 8216.566138800012, "count": 238, "self": 827.3463414000198, "children": { "TorchPOCAOptimizer.update": { "total": 7389.219797399992, "count": 7140, "self": 7389.219797399992 } } } } } } }, "trainer_threads": { "total": 1.4999986888142303e-06, "count": 1, "self": 1.4999986888142303e-06 }, "TrainerController._save_models": { "total": 0.146097999999256, "count": 1, "self": 0.0029740999980276683, "children": { "RLTrainer._checkpoint": { "total": 0.14312390000122832, "count": 1, "self": 0.14312390000122832 } } } } } } }