{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5660171508789062, "min": 1.5396820306777954, "max": 1.880081295967102, "count": 198 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31320.34375, "min": 29534.00390625, "max": 41144.2421875, "count": 198 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 63.835443037974684, "min": 42.70175438596491, "max": 84.71666666666667, "count": 198 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20172.0, "min": 16128.0, "max": 20528.0, "count": 198 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1417.6097296242715, "min": 1380.403699591196, "max": 1456.4866303781612, "count": 198 }, "SoccerTwos.Self-play.ELO.sum": { "value": 223982.3372806349, "min": 167199.51708247018, "max": 323254.78982444253, "count": 198 }, "SoccerTwos.Step.mean": { "value": 5529938.0, "min": 3559972.0, "max": 5529938.0, "count": 198 }, "SoccerTwos.Step.sum": { "value": 5529938.0, "min": 3559972.0, "max": 5529938.0, "count": 198 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.051855020225048065, "min": -0.14628547430038452, "max": 0.0822330117225647, "count": 198 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -8.193093299865723, "min": -28.37938117980957, "max": 16.035436630249023, "count": 198 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.042027898132801056, "min": -0.1427212804555893, "max": 0.08749193698167801, "count": 198 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.640408039093018, "min": -27.68792724609375, "max": 17.060928344726562, "count": 198 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 198 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 198 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09168860882143431, "min": -0.3312575988769531, "max": 0.3173333341425115, "count": 198 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -14.486800193786621, "min": -54.38579994440079, "max": 52.360000133514404, "count": 198 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09168860882143431, "min": -0.3312575988769531, "max": 0.3173333341425115, "count": 198 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -14.486800193786621, "min": -54.38579994440079, "max": 52.360000133514404, "count": 198 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 198 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 198 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.026255231936617444, "min": 0.01627497440543569, "max": 0.03656857611301045, "count": 191 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.026255231936617444, "min": 0.01627497440543569, "max": 0.03656857611301045, "count": 191 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09653884669144948, "min": 0.07564474120736123, "max": 0.12114908628993565, "count": 191 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09653884669144948, "min": 0.07564474120736123, "max": 0.12114908628993565, "count": 191 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10025102198123932, "min": 0.07619098275899887, "max": 0.1247354370576364, "count": 191 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10025102198123932, "min": 0.07619098275899887, "max": 0.1247354370576364, "count": 191 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 191 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 191 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 191 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 191 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 191 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 191 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1732095102", "python_version": "3.10.4 (tags/v3.10.4:9d38120, Mar 23 2022, 23:13:41) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "D:\\python projects\\ml-agents\\venv\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1732101370" }, "total": 6268.3186942000175, "count": 1, "self": 10.264327400014736, "children": { "run_training.setup": { "total": 0.3097142999758944, "count": 1, "self": 0.3097142999758944 }, "TrainerController.start_learning": { "total": 6257.744652500027, "count": 1, "self": 3.813153204973787, "children": { "TrainerController._reset_env": { "total": 11.315755600109696, "count": 11, "self": 11.315755600109696 }, "TrainerController.advance": { "total": 6242.059609094984, "count": 137126, "self": 3.7370750026311725, "children": { "env_step": { "total": 2836.0991703160107, "count": 137126, "self": 2218.9756366901565, "children": { "SubprocessEnvManager._take_step": { "total": 614.819088418386, "count": 137126, "self": 22.754441584693268, "children": { "TorchPolicy.evaluate": { "total": 592.0646468336927, "count": 248380, "self": 592.0646468336927 } } }, "workers": { "total": 2.304445207468234, "count": 137125, "self": 0.0, "children": { "worker_root": { "total": 6246.121647206368, "count": 137125, "is_parallel": true, "self": 4446.1522600069875, "children": { "steps_from_proto": { "total": 0.020320799783803523, "count": 22, "is_parallel": true, "self": 0.0038775004213675857, "children": { "_process_rank_one_or_two_observation": { "total": 0.016443299362435937, "count": 88, "is_parallel": true, "self": 0.016443299362435937 } } }, "UnityEnvironment.step": { "total": 1799.9490663995966, "count": 137125, "is_parallel": true, "self": 95.17972115217708, "children": { "UnityEnvironment._generate_step_input": { "total": 73.22999456862453, "count": 137125, "is_parallel": true, "self": 73.22999456862453 }, "communicator.exchange": { "total": 1345.3410510788672, "count": 137125, "is_parallel": true, "self": 1345.3410510788672 }, "steps_from_proto": { "total": 286.19829959992785, "count": 274250, "is_parallel": true, "self": 55.273062570835464, "children": { "_process_rank_one_or_two_observation": { "total": 230.9252370290924, "count": 1097000, "is_parallel": true, "self": 230.9252370290924 } } } } } } } } } } }, "trainer_advance": { "total": 3402.223363776342, "count": 137125, "self": 25.176138061331585, "children": { "process_trajectory": { "total": 673.8780544148758, "count": 137125, "self": 669.0686950148083, "children": { "RLTrainer._checkpoint": { "total": 4.809359400067478, "count": 4, "self": 4.809359400067478 } } }, "_update_policy": { "total": 2703.1691713001346, "count": 191, "self": 285.2503954063868, "children": { "TorchPOCAOptimizer.update": { "total": 2417.918775893748, "count": 5562, "self": 2417.918775893748 } } } } } } }, "trainer_threads": { "total": 1.200009137392044e-06, "count": 1, "self": 1.200009137392044e-06 }, "TrainerController._save_models": { "total": 0.5561333999503404, "count": 1, "self": 0.2464682999998331, "children": { "RLTrainer._checkpoint": { "total": 0.3096650999505073, "count": 1, "self": 0.3096650999505073 } } } } } } }