{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4813734292984009, "min": 1.4523465633392334, "max": 1.8827192783355713, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30291.123046875, "min": 27888.0, "max": 40787.23046875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 42.61739130434783, "min": 35.40875912408759, "max": 62.2125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19604.0, "min": 18192.0, "max": 20496.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1577.3278964698527, "min": 1505.856633164282, "max": 1607.9342147062453, "count": 500 }, "SoccerTwos.Self-play.ELO.sum": { "value": 362785.4161880661, "min": 241869.99428611956, "max": 428521.8946358607, "count": 500 }, "SoccerTwos.Step.mean": { "value": 9999972.0, "min": 5009954.0, "max": 9999972.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 9999972.0, "min": 5009954.0, "max": 9999972.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.016964344307780266, "min": -0.09779278188943863, "max": 0.09828563779592514, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.901799201965332, "min": -22.003376007080078, "max": 20.639984130859375, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.01681143417954445, "min": -0.09867770969867706, "max": 0.09790761768817902, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.8666298389434814, "min": -22.202484130859375, "max": 20.56060028076172, "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": -0.018830435431521873, "min": -0.28656395542067153, "max": 0.254424856207465, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.3310001492500305, "min": -57.68040007352829, "max": 50.397399604320526, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.018830435431521873, "min": -0.28656395542067153, "max": 0.254424856207465, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.3310001492500305, "min": -57.68040007352829, "max": 50.397399604320526, "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": 0.014714702679258253, "min": 0.008386772028138189, "max": 0.021870147617947724, "count": 243 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014714702679258253, "min": 0.008386772028138189, "max": 0.021870147617947724, "count": 243 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.12173405372434193, "min": 0.10558312717411253, "max": 0.13476302888658312, "count": 243 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.12173405372434193, "min": 0.10558312717411253, "max": 0.13476302888658312, "count": 243 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.12211715016100141, "min": 0.10619260908828841, "max": 0.13504979014396667, "count": 243 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.12211715016100141, "min": 0.10619260908828841, "max": 0.13504979014396667, "count": 243 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 6.921996543998919e-08, "min": 6.921996543998919e-08, "max": 9.958629020688e-05, "count": 243 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 6.921996543998919e-08, "min": 6.921996543998919e-08, "max": 9.958629020688e-05, "count": 243 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10005183999999999, "min": 0.10005183999999999, "max": 0.17468968000000004, "count": 243 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.10005183999999999, "min": 0.10005183999999999, "max": 0.17468968000000004, "count": 243 }, "SoccerTwos.Policy.Beta.mean": { "value": 1.1378943999999786e-05, "min": 1.1378943999999786e-05, "max": 0.001996745488000001, "count": 243 }, "SoccerTwos.Policy.Beta.sum": { "value": 1.1378943999999786e-05, "min": 1.1378943999999786e-05, "max": 0.001996745488000001, "count": 243 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694236457", "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\\voyz\\.virtualenvs\\deep_rl_course_u7_p39\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos5 --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1694258857" }, "total": 22401.2324006, "count": 1, "self": 0.5248601000021154, "children": { "run_training.setup": { "total": 0.24669090000000082, "count": 1, "self": 0.24669090000000082 }, "TrainerController.start_learning": { "total": 22400.4608496, "count": 1, "self": 12.748866300415102, "children": { "TrainerController._reset_env": { "total": 10.469387500001687, "count": 18, "self": 10.469387500001687 }, "TrainerController.advance": { "total": 22376.872806599582, "count": 356113, "self": 12.226129598384432, "children": { "env_step": { "total": 16583.080249001483, "count": 356113, "self": 10007.274636201531, "children": { "SubprocessEnvManager._take_step": { "total": 6568.347290199748, "count": 356113, "self": 83.64209400055552, "children": { "TorchPolicy.evaluate": { "total": 6484.705196199193, "count": 626198, "self": 6484.705196199193 } } }, "workers": { "total": 7.458322600202077, "count": 356113, "self": 0.0, "children": { "worker_root": { "total": 22370.41648019894, "count": 356113, "is_parallel": true, "self": 13851.782743698908, "children": { "steps_from_proto": { "total": 0.05337660000131006, "count": 36, "is_parallel": true, "self": 0.011230800010800124, "children": { "_process_rank_one_or_two_observation": { "total": 0.042145799990509936, "count": 144, "is_parallel": true, "self": 0.042145799990509936 } } }, "UnityEnvironment.step": { "total": 8518.58035990003, "count": 356113, "is_parallel": true, "self": 328.68323039905226, "children": { "UnityEnvironment._generate_step_input": { "total": 233.64260100085235, "count": 356113, "is_parallel": true, "self": 233.64260100085235 }, "communicator.exchange": { "total": 6884.315014400223, "count": 356113, "is_parallel": true, "self": 6884.315014400223 }, "steps_from_proto": { "total": 1071.9395140999022, "count": 712226, "is_parallel": true, "self": 230.18878070043002, "children": { "_process_rank_one_or_two_observation": { "total": 841.7507333994722, "count": 2848904, "is_parallel": true, "self": 841.7507333994722 } } } } } } } } } } }, "trainer_advance": { "total": 5781.5664279997145, "count": 356113, "self": 79.6152038996297, "children": { "process_trajectory": { "total": 3739.4091631001056, "count": 356113, "self": 3735.5494080001117, "children": { "RLTrainer._checkpoint": { "total": 3.8597550999938903, "count": 10, "self": 3.8597550999938903 } } }, "_update_policy": { "total": 1962.542060999979, "count": 243, "self": 1257.5645117999559, "children": { "TorchPOCAOptimizer.update": { "total": 704.9775492000231, "count": 4377, "self": 704.9775492000231 } } } } } } }, "trainer_threads": { "total": 1.2000018614344299e-06, "count": 1, "self": 1.2000018614344299e-06 }, "TrainerController._save_models": { "total": 0.36978799999997136, "count": 1, "self": 0.007586499999888474, "children": { "RLTrainer._checkpoint": { "total": 0.3622015000000829, "count": 1, "self": 0.3622015000000829 } } } } } } }