{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.958897590637207, "min": 1.958897590637207, "max": 3.295691728591919, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40180.90625, "min": 27310.2109375, "max": 114069.5703125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 58.75, "min": 42.18103448275862, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19740.0, "min": 13868.0, "max": 26396.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1510.6785520503622, "min": 1197.7163201944231, "max": 1510.7273914316831, "count": 488 }, "SoccerTwos.Self-play.ELO.sum": { "value": 253793.99674446083, "min": 2399.754687971731, "max": 344817.26437304646, "count": 488 }, "SoccerTwos.Step.mean": { "value": 4999823.0, "min": 9216.0, "max": 4999823.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999823.0, "min": 9216.0, "max": 4999823.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.06482566148042679, "min": -0.1127309650182724, "max": 0.13317570090293884, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 10.955536842346191, "min": -18.26241683959961, "max": 19.894054412841797, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.06249595806002617, "min": -0.11246709525585175, "max": 0.13988922536373138, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 10.561817169189453, "min": -18.219669342041016, "max": 19.86170196533203, "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": 0.016142012099542562, "min": -0.75, "max": 0.47272131579821225, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 2.728000044822693, "min": -51.80399978160858, "max": 54.885600090026855, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.016142012099542562, "min": -0.75, "max": 0.47272131579821225, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 2.728000044822693, "min": -51.80399978160858, "max": 54.885600090026855, "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": 0.019074402245072026, "min": 0.011203128710621967, "max": 0.022758910306341324, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019074402245072026, "min": 0.011203128710621967, "max": 0.022758910306341324, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0759902315835158, "min": 0.00011842909461847739, "max": 0.09545681774616241, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0759902315835158, "min": 0.00011842909461847739, "max": 0.09545681774616241, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07670819784204165, "min": 0.0001206130289574503, "max": 0.09665488079190254, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.07670819784204165, "min": 0.0001206130289574503, "max": 0.09665488079190254, "count": 239 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 239 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 239 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1706892802", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\ksmsu\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1706904037" }, "total": 11234.566408800078, "count": 1, "self": 1.690612900070846, "children": { "run_training.setup": { "total": 0.09289009997155517, "count": 1, "self": 0.09289009997155517 }, "TrainerController.start_learning": { "total": 11232.782905800035, "count": 1, "self": 8.93734723329544, "children": { "TrainerController._reset_env": { "total": 4.484800899983384, "count": 25, "self": 4.484800899983384 }, "TrainerController.advance": { "total": 11219.232637566747, "count": 340045, "self": 8.987933204043657, "children": { "env_step": { "total": 5302.118825148093, "count": 340045, "self": 4140.895049570827, "children": { "SubprocessEnvManager._take_step": { "total": 1155.8955111680552, "count": 340045, "self": 44.82748165098019, "children": { "TorchPolicy.evaluate": { "total": 1111.068029517075, "count": 631986, "self": 1111.068029517075 } } }, "workers": { "total": 5.328264409210533, "count": 340045, "self": 0.0, "children": { "worker_root": { "total": 11218.552969845128, "count": 340045, "is_parallel": true, "self": 7970.805876631057, "children": { "steps_from_proto": { "total": 0.03280089981853962, "count": 50, "is_parallel": true, "self": 0.007205399568192661, "children": { "_process_rank_one_or_two_observation": { "total": 0.02559550025034696, "count": 200, "is_parallel": true, "self": 0.02559550025034696 } } }, "UnityEnvironment.step": { "total": 3247.714292314253, "count": 340045, "is_parallel": true, "self": 146.5276657892391, "children": { "UnityEnvironment._generate_step_input": { "total": 117.13562141440343, "count": 340045, "is_parallel": true, "self": 117.13562141440343 }, "communicator.exchange": { "total": 2531.7168078834657, "count": 340045, "is_parallel": true, "self": 2531.7168078834657 }, "steps_from_proto": { "total": 452.3341972271446, "count": 680090, "is_parallel": true, "self": 97.30342673347332, "children": { "_process_rank_one_or_two_observation": { "total": 355.0307704936713, "count": 2720360, "is_parallel": true, "self": 355.0307704936713 } } } } } } } } } } }, "trainer_advance": { "total": 5908.125879214611, "count": 340045, "self": 67.7687984801596, "children": { "process_trajectory": { "total": 1096.434175533941, "count": 340045, "self": 1095.0075900340453, "children": { "RLTrainer._checkpoint": { "total": 1.4265854998957366, "count": 10, "self": 1.4265854998957366 } } }, "_update_policy": { "total": 4743.92290520051, "count": 239, "self": 687.9365829988383, "children": { "TorchPOCAOptimizer.update": { "total": 4055.986322201672, "count": 7173, "self": 4055.986322201672 } } } } } } }, "trainer_threads": { "total": 1.00000761449337e-06, "count": 1, "self": 1.00000761449337e-06 }, "TrainerController._save_models": { "total": 0.12811910000164062, "count": 1, "self": 0.015942999976687133, "children": { "RLTrainer._checkpoint": { "total": 0.11217610002495348, "count": 1, "self": 0.11217610002495348 } } } } } } }