{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": -3.576278402306343e-07, "min": -3.576278402306343e-07, "max": -3.562342953955522e-07, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": -0.00983047392219305, "min": -0.019329069182276726, "max": -0.0004692077054642141, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 656.5, "min": 317.125, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21008.0, "min": 12744.0, "max": 31936.0, "count": 500 }, "SoccerTwos.Step.mean": { "value": 14999754.0, "min": 10009865.0, "max": 14999754.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 14999754.0, "min": 10009865.0, "max": 14999754.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 23.871986389160156, "min": -47.09134292602539, "max": 83.98540496826172, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 381.9517822265625, "min": -640.2660522460938, "max": 1335.951416015625, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 24.30628776550293, "min": -45.15403366088867, "max": 84.21553802490234, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 388.9006042480469, "min": -615.5823974609375, "max": 1283.3922119140625, "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": 0.10167500376701355, "min": -0.4444444444444444, "max": 0.4201333390341865, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 1.6268000602722168, "min": -10.05680000782013, "max": 7.5624001026153564, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.10167500376701355, "min": -0.4444444444444444, "max": 0.4201333390341865, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 1.6268000602722168, "min": -10.05680000782013, "max": 7.5624001026153564, "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.Self-play.ELO.mean": { "value": 1142.42135593036, "min": 1132.9015815683288, "max": 1166.151622189439, "count": 374 }, "SoccerTwos.Self-play.ELO.sum": { "value": 6854.528135582161, "min": 2265.8031631366575, "max": 20463.870130720632, "count": 374 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019528812146745622, "min": 0.010530641971854493, "max": 0.024130393659773593, "count": 231 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019528812146745622, "min": 0.010530641971854493, "max": 0.024130393659773593, "count": 231 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 123.05066089630127, "min": 0.006790764071047306, "max": 69264.42675771118, "count": 231 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 123.05066089630127, "min": 0.006790764071047306, "max": 69264.42675771118, "count": 231 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 150.42002614339194, "min": 0.008305311598815025, "max": 62744.35670034488, "count": 231 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 150.42002614339194, "min": 0.008305311598815025, "max": 62744.35670034488, "count": 231 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 231 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 231 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 231 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 231 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 231 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 231 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1723915684", "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\\Juan\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1723953013" }, "total": 37331.6693596, "count": 1, "self": 1.0257882000005338, "children": { "run_training.setup": { "total": 0.1769217000110075, "count": 1, "self": 0.1769217000110075 }, "TrainerController.start_learning": { "total": 37330.466649699985, "count": 1, "self": 12.577865000523161, "children": { "TrainerController._reset_env": { "total": 16.64005550008733, "count": 26, "self": 16.64005550008733 }, "TrainerController.advance": { "total": 37301.08845649936, "count": 326998, "self": 13.247424681525445, "children": { "env_step": { "total": 10426.639386609284, "count": 326998, "self": 8144.437864703708, "children": { "SubprocessEnvManager._take_step": { "total": 2273.953988297988, "count": 326998, "self": 89.04225159110501, "children": { "TorchPolicy.evaluate": { "total": 2184.911736706883, "count": 648674, "self": 2184.911736706883 } } }, "workers": { "total": 8.247533607587684, "count": 326998, "self": 0.0, "children": { "worker_root": { "total": 37298.17909569258, "count": 326998, "is_parallel": true, "self": 30809.936276192195, "children": { "steps_from_proto": { "total": 0.05289510000147857, "count": 52, "is_parallel": true, "self": 0.010617799882311374, "children": { "_process_rank_one_or_two_observation": { "total": 0.042277300119167194, "count": 208, "is_parallel": true, "self": 0.042277300119167194 } } }, "UnityEnvironment.step": { "total": 6488.189924400387, "count": 326998, "is_parallel": true, "self": 346.37758579207, "children": { "UnityEnvironment._generate_step_input": { "total": 292.7887483941158, "count": 326998, "is_parallel": true, "self": 292.7887483941158 }, "communicator.exchange": { "total": 4759.800860201853, "count": 326998, "is_parallel": true, "self": 4759.800860201853 }, "steps_from_proto": { "total": 1089.2227300123486, "count": 653996, "is_parallel": true, "self": 197.67923843176686, "children": { "_process_rank_one_or_two_observation": { "total": 891.5434915805818, "count": 2615984, "is_parallel": true, "self": 891.5434915805818 } } } } } } } } } } }, "trainer_advance": { "total": 26861.20164520855, "count": 326998, "self": 93.12427091199788, "children": { "process_trajectory": { "total": 2941.646539996378, "count": 326998, "self": 2940.1027289963677, "children": { "RLTrainer._checkpoint": { "total": 1.5438110000104643, "count": 10, "self": 1.5438110000104643 } } }, "_update_policy": { "total": 23826.430834300176, "count": 231, "self": 934.135846501129, "children": { "TorchPOCAOptimizer.update": { "total": 22892.294987799047, "count": 6930, "self": 22892.294987799047 } } } } } } }, "trainer_threads": { "total": 1.700012944638729e-06, "count": 1, "self": 1.700012944638729e-06 }, "TrainerController._save_models": { "total": 0.1602710000006482, "count": 1, "self": 0.010993000003509223, "children": { "RLTrainer._checkpoint": { "total": 0.14927799999713898, "count": 1, "self": 0.14927799999713898 } } } } } } }