{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5186562538146973, "min": 1.4608826637268066, "max": 3.29573392868042, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28526.439453125, "min": 14313.00390625, "max": 105463.4765625, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 58.34146341463415, "min": 41.547008547008545, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19136.0, "min": 12580.0, "max": 29324.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1814.8166567919093, "min": 1198.5013186380206, "max": 1826.4453512768232, "count": 4992 }, "SoccerTwos.Self-play.ELO.sum": { "value": 297629.9317138731, "min": 2397.397599728552, "max": 399614.9304489801, "count": 4992 }, "SoccerTwos.Step.mean": { "value": 49999892.0, "min": 9948.0, "max": 49999892.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999892.0, "min": 9948.0, "max": 49999892.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.013297130353748798, "min": -0.1366938203573227, "max": 0.20098116993904114, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.194026470184326, "min": -26.518600463867188, "max": 23.02322006225586, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.012455220334231853, "min": -0.1367611289024353, "max": 0.20110416412353516, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.0551114082336426, "min": -26.531660079956055, "max": 22.902568817138672, "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": -0.10468121297431715, "min": -0.6153333319558038, "max": 0.5053072429221609, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -17.27240014076233, "min": -62.537400007247925, "max": 62.218000173568726, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.10468121297431715, "min": -0.6153333319558038, "max": 0.5053072429221609, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -17.27240014076233, "min": -62.537400007247925, "max": 62.218000173568726, "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": 0.017618808253124976, "min": 0.008969860304205213, "max": 0.028073993038075666, "count": 2424 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017618808253124976, "min": 0.008969860304205213, "max": 0.028073993038075666, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10675406306982041, "min": 0.00018999845245465014, "max": 0.12937953174114228, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10675406306982041, "min": 0.00018999845245465014, "max": 0.12937953174114228, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10732563734054565, "min": 0.0001875025438494049, "max": 0.13031024982531866, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10732563734054565, "min": 0.0001875025438494049, "max": 0.13031024982531866, "count": 2424 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2424 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2424 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676233961", "python_version": "3.8.16 (default, Jan 17 2023, 22:25:28) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Kaush\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=pocatrainergoal3 --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+cu117", "numpy_version": "1.21.2", "end_time_seconds": "1676328405" }, "total": 94445.66438500001, "count": 1, "self": 0.4728964000096312, "children": { "run_training.setup": { "total": 0.08000050000000014, "count": 1, "self": 0.08000050000000014 }, "TrainerController.start_learning": { "total": 94445.1114881, "count": 1, "self": 76.53268388766446, "children": { "TrainerController._reset_env": { "total": 8.249404499986603, "count": 250, "self": 8.249404499986603 }, "TrainerController.advance": { "total": 94360.22281491235, "count": 3458226, "self": 70.389487003049, "children": { "env_step": { "total": 65296.17353700749, "count": 3458226, "self": 39011.75240709914, "children": { "SubprocessEnvManager._take_step": { "total": 26239.15809810668, "count": 3458226, "self": 433.13853791115616, "children": { "TorchPolicy.evaluate": { "total": 25806.019560195524, "count": 6279102, "self": 25806.019560195524 } } }, "workers": { "total": 45.263031801666145, "count": 3458226, "self": 0.0, "children": { "worker_root": { "total": 94350.69593631088, "count": 3458226, "is_parallel": true, "self": 63576.25346989637, "children": { "steps_from_proto": { "total": 0.3665863999490133, "count": 500, "is_parallel": true, "self": 0.08069739998306691, "children": { "_process_rank_one_or_two_observation": { "total": 0.2858889999659464, "count": 2000, "is_parallel": true, "self": 0.2858889999659464 } } }, "UnityEnvironment.step": { "total": 30774.075880014556, "count": 3458226, "is_parallel": true, "self": 1489.1386516420243, "children": { "UnityEnvironment._generate_step_input": { "total": 1623.7819271873745, "count": 3458226, "is_parallel": true, "self": 1623.7819271873745 }, "communicator.exchange": { "total": 22838.94724170412, "count": 3458226, "is_parallel": true, "self": 22838.94724170412 }, "steps_from_proto": { "total": 4822.208059481035, "count": 6916452, "is_parallel": true, "self": 1035.2841259896022, "children": { "_process_rank_one_or_two_observation": { "total": 3786.9239334914328, "count": 27665808, "is_parallel": true, "self": 3786.9239334914328 } } } } } } } } } } }, "trainer_advance": { "total": 28993.65979090182, "count": 3458226, "self": 483.21517590406074, "children": { "process_trajectory": { "total": 12961.061185397662, "count": 3458226, "self": 12947.260951297643, "children": { "RLTrainer._checkpoint": { "total": 13.800234100019793, "count": 100, "self": 13.800234100019793 } } }, "_update_policy": { "total": 15549.383429600097, "count": 2424, "self": 10259.888580301953, "children": { "TorchPOCAOptimizer.update": { "total": 5289.494849298144, "count": 72726, "self": 5289.494849298144 } } } } } } }, "trainer_threads": { "total": 2.7999922167509794e-06, "count": 1, "self": 2.7999922167509794e-06 }, "TrainerController._save_models": { "total": 0.10658199999306817, "count": 1, "self": 0.0031098999897949398, "children": { "RLTrainer._checkpoint": { "total": 0.10347210000327323, "count": 1, "self": 0.10347210000327323 } } } } } } }