{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8859961032867432, "min": 0.7960292100906372, "max": 3.2957451343536377, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37056.05078125, "min": 10420.7392578125, "max": 160892.15625, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 61.69230769230769, "min": 47.300970873786405, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19248.0, "min": 12720.0, "max": 30472.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1596.9313248102283, "min": 1181.879118812825, "max": 1607.88234923467, "count": 1668 }, "SoccerTwos.Self-play.ELO.sum": { "value": 249121.2866703956, "min": 2363.75823762565, "max": 320736.99087702495, "count": 1668 }, "SoccerTwos.Step.mean": { "value": 49999941.0, "min": 9252.0, "max": 49999941.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999941.0, "min": 9252.0, "max": 49999941.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0425206795334816, "min": -0.12837325036525726, "max": 0.15666325390338898, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -6.675746917724609, "min": -18.100627899169922, "max": 27.25940704345703, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0382288359105587, "min": -0.1278502345085144, "max": 0.16222737729549408, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.001927375793457, "min": -18.455331802368164, "max": 28.227563858032227, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.30523311864038943, "min": -0.6923076923076923, "max": 0.42062222295337254, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -47.92159962654114, "min": -47.92159962654114, "max": 47.269000351428986, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.30523311864038943, "min": -0.6923076923076923, "max": 0.42062222295337254, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -47.92159962654114, "min": -47.92159962654114, "max": 47.269000351428986, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014865773305064067, "min": 0.009734752150446486, "max": 0.02486639428922596, "count": 2314 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014865773305064067, "min": 0.009734752150446486, "max": 0.02486639428922596, "count": 2314 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09687695155541103, "min": 5.549574153806044e-12, "max": 0.10573716560999552, "count": 2314 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09687695155541103, "min": 5.549574153806044e-12, "max": 0.10573716560999552, "count": 2314 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09823337495326996, "min": 8.280764818060135e-12, "max": 0.10774662320812543, "count": 2314 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09823337495326996, "min": 8.280764818060135e-12, "max": 0.10774662320812543, "count": 2314 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2314 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2314 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2314 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2314 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2314 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2314 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689125754", "python_version": "3.9.13 (tags/v3.9.13:6de2ca5, May 17 2022, 16:36:42) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\vitco\\Desktop\\SoccerTwos\\env\\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+cu116", "numpy_version": "1.21.2", "end_time_seconds": "1689205231" }, "total": 79476.61104039999, "count": 1, "self": 0.7239865999872563, "children": { "run_training.setup": { "total": 0.2028278000000001, "count": 1, "self": 0.2028278000000001 }, "TrainerController.start_learning": { "total": 79475.684226, "count": 1, "self": 53.68059590390476, "children": { "TrainerController._reset_env": { "total": 17.12137330000531, "count": 249, "self": 17.12137330000531 }, "TrainerController.advance": { "total": 79404.7220559961, "count": 3278979, "self": 58.7541511883901, "children": { "env_step": { "total": 56214.57777440655, "count": 3278979, "self": 34536.39524380873, "children": { "SubprocessEnvManager._take_step": { "total": 21642.040069300623, "count": 3278979, "self": 359.92690518921154, "children": { "TorchPolicy.evaluate": { "total": 21282.11316411141, "count": 6431088, "self": 21282.11316411141 } } }, "workers": { "total": 36.14246129719899, "count": 3278979, "self": 0.0, "children": { "worker_root": { "total": 79379.58762889986, "count": 3278979, "is_parallel": true, "self": 51420.96723030831, "children": { "steps_from_proto": { "total": 0.5842672999857501, "count": 498, "is_parallel": true, "self": 0.11798829990786297, "children": { "_process_rank_one_or_two_observation": { "total": 0.46627900007788714, "count": 1992, "is_parallel": true, "self": 0.46627900007788714 } } }, "UnityEnvironment.step": { "total": 27958.036131291556, "count": 3278979, "is_parallel": true, "self": 1510.600279377246, "children": { "UnityEnvironment._generate_step_input": { "total": 1552.2331909067102, "count": 3278979, "is_parallel": true, "self": 1552.2331909067102 }, "communicator.exchange": { "total": 20337.390693502173, "count": 3278979, "is_parallel": true, "self": 20337.390693502173 }, "steps_from_proto": { "total": 4557.811967505427, "count": 6557958, "is_parallel": true, "self": 949.4219691056983, "children": { "_process_rank_one_or_two_observation": { "total": 3608.3899983997285, "count": 26231832, "is_parallel": true, "self": 3608.3899983997285 } } } } } } } } } } }, "trainer_advance": { "total": 23131.390130401163, "count": 3278979, "self": 429.52601460448204, "children": { "process_trajectory": { "total": 5416.983307796469, "count": 3278979, "self": 5399.051477096455, "children": { "RLTrainer._checkpoint": { "total": 17.931830700013734, "count": 100, "self": 17.931830700013734 } } }, "_update_policy": { "total": 17284.880808000213, "count": 2314, "self": 7338.387878698481, "children": { "TorchPOCAOptimizer.update": { "total": 9946.492929301732, "count": 69420, "self": 9946.492929301732 } } } } } } }, "trainer_threads": { "total": 4.999892553314567e-07, "count": 1, "self": 4.999892553314567e-07 }, "TrainerController._save_models": { "total": 0.16020030000072438, "count": 1, "self": 0.011720599999534898, "children": { "RLTrainer._checkpoint": { "total": 0.14847970000118949, "count": 1, "self": 0.14847970000118949 } } } } } } }