{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.219115734100342, "min": 2.19679856300354, "max": 3.2957592010498047, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 44879.3984375, "min": 20429.765625, "max": 131154.125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.28260869565217, "min": 43.705357142857146, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19976.0, "min": 13640.0, "max": 28836.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1514.635325257901, "min": 1175.5303149514862, "max": 1540.5535986484128, "count": 461 }, "SoccerTwos.Self-play.ELO.sum": { "value": 278692.8998474538, "min": 2352.708475439669, "max": 332456.12015789293, "count": 461 }, "SoccerTwos.Step.mean": { "value": 4999986.0, "min": 9434.0, "max": 4999986.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999986.0, "min": 9434.0, "max": 4999986.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.009690292179584503, "min": -0.06676390767097473, "max": 0.2656790018081665, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.7830138206481934, "min": -11.13835334777832, "max": 36.33460998535156, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.009328517131507397, "min": -0.07028283923864365, "max": 0.2686382532119751, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.716447114944458, "min": -12.013956069946289, "max": 36.718902587890625, "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": -0.0057891289825024814, "min": -0.6652000000079473, "max": 0.5766857140942624, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.0651997327804565, "min": -39.243200063705444, "max": 76.6991999745369, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.0057891289825024814, "min": -0.6652000000079473, "max": 0.5766857140942624, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.0651997327804565, "min": -39.243200063705444, "max": 76.6991999745369, "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": 0.01664948812297856, "min": 0.011905774932044248, "max": 0.02285748055825631, "count": 237 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01664948812297856, "min": 0.011905774932044248, "max": 0.02285748055825631, "count": 237 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10561632787187894, "min": 2.331003175489362e-06, "max": 0.11489342699448267, "count": 237 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10561632787187894, "min": 2.331003175489362e-06, "max": 0.11489342699448267, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10754233524203301, "min": 2.4531511750562156e-06, "max": 0.11718783502777418, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10754233524203301, "min": 2.4531511750562156e-06, "max": 0.11718783502777418, "count": 237 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 237 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 237 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 237 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 237 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 237 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 237 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1685053186", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\jwood\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu117", "numpy_version": "1.21.2", "end_time_seconds": "1685060352" }, "total": 7165.688564499999, "count": 1, "self": 0.5273317000001043, "children": { "run_training.setup": { "total": 0.08869229999999995, "count": 1, "self": 0.08869229999999995 }, "TrainerController.start_learning": { "total": 7165.072540499999, "count": 1, "self": 6.119253500058221, "children": { "TrainerController._reset_env": { "total": 4.80170039999751, "count": 25, "self": 4.80170039999751 }, "TrainerController.advance": { "total": 7154.003809099944, "count": 333064, "self": 5.9434175999886065, "children": { "env_step": { "total": 5349.485794500149, "count": 333064, "self": 3537.9022568000237, "children": { "SubprocessEnvManager._take_step": { "total": 1807.5844411002647, "count": 333064, "self": 36.23928330086369, "children": { "TorchPolicy.evaluate": { "total": 1771.345157799401, "count": 638248, "self": 1771.345157799401 } } }, "workers": { "total": 3.999096599860521, "count": 333064, "self": 0.0, "children": { "worker_root": { "total": 7153.6843497000555, "count": 333064, "is_parallel": true, "self": 4334.950232100071, "children": { "steps_from_proto": { "total": 0.03446980000073152, "count": 50, "is_parallel": true, "self": 0.0075197000066578035, "children": { "_process_rank_one_or_two_observation": { "total": 0.026950099994073717, "count": 200, "is_parallel": true, "self": 0.026950099994073717 } } }, "UnityEnvironment.step": { "total": 2818.6996477999837, "count": 333064, "is_parallel": true, "self": 137.64734230070553, "children": { "UnityEnvironment._generate_step_input": { "total": 116.67095019972939, "count": 333064, "is_parallel": true, "self": 116.67095019972939 }, "communicator.exchange": { "total": 2128.998269599813, "count": 333064, "is_parallel": true, "self": 2128.998269599813 }, "steps_from_proto": { "total": 435.38308569973583, "count": 666128, "is_parallel": true, "self": 93.03014329988093, "children": { "_process_rank_one_or_two_observation": { "total": 342.3529423998549, "count": 2664512, "is_parallel": true, "self": 342.3529423998549 } } } } } } } } } } }, "trainer_advance": { "total": 1798.5745969998068, "count": 333064, "self": 43.89163129996382, "children": { "process_trajectory": { "total": 567.0804893998438, "count": 333064, "self": 564.9522061998447, "children": { "RLTrainer._checkpoint": { "total": 2.128283199999146, "count": 10, "self": 2.128283199999146 } } }, "_update_policy": { "total": 1187.6024762999991, "count": 237, "self": 663.3542683999674, "children": { "TorchPOCAOptimizer.update": { "total": 524.2482079000317, "count": 7110, "self": 524.2482079000317 } } } } } } }, "trainer_threads": { "total": 6.999998731771484e-07, "count": 1, "self": 6.999998731771484e-07 }, "TrainerController._save_models": { "total": 0.14777679999951943, "count": 1, "self": 0.0016951999996308587, "children": { "RLTrainer._checkpoint": { "total": 0.14608159999988857, "count": 1, "self": 0.14608159999988857 } } } } } } }