{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6436563730239868, "min": 1.5766630172729492, "max": 3.2957727909088135, "count": 836 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33925.06640625, "min": 27373.46484375, "max": 108274.7890625, "count": 836 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 56.241379310344826, "min": 46.235849056603776, "max": 999.0, "count": 836 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19572.0, "min": 16624.0, "max": 24692.0, "count": 836 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1622.901046867177, "min": 1183.1620344266842, "max": 1660.0724597833855, "count": 834 }, "SoccerTwos.Self-play.ELO.sum": { "value": 282384.7821548888, "min": 2367.788579599301, "max": 323841.91322314646, "count": 834 }, "SoccerTwos.Step.mean": { "value": 8359982.0, "min": 9364.0, "max": 8359982.0, "count": 836 }, "SoccerTwos.Step.sum": { "value": 8359982.0, "min": 9364.0, "max": 8359982.0, "count": 836 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.04412328451871872, "min": -0.13746853172779083, "max": 0.2039482593536377, "count": 836 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -7.6774516105651855, "min": -22.957244873046875, "max": 28.05706787109375, "count": 836 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03761598840355873, "min": -0.13524287939071655, "max": 0.20287510752677917, "count": 836 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.545182228088379, "min": -22.585559844970703, "max": 28.808265686035156, "count": 836 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 836 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 836 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.07114252824892943, "min": -0.5833333333333334, "max": 0.4089764715994106, "count": 836 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 12.37879991531372, "min": -55.82079941034317, "max": 54.98859965801239, "count": 836 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.07114252824892943, "min": -0.5833333333333334, "max": 0.4089764715994106, "count": 836 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 12.37879991531372, "min": -55.82079941034317, "max": 54.98859965801239, "count": 836 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 836 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 836 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015712379955220967, "min": 0.01139993552060332, "max": 0.025473337310055893, "count": 403 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015712379955220967, "min": 0.01139993552060332, "max": 0.025473337310055893, "count": 403 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08840486680467924, "min": 0.0008984813781959625, "max": 0.11362483402093251, "count": 403 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08840486680467924, "min": 0.0008984813781959625, "max": 0.11362483402093251, "count": 403 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09042802080512047, "min": 0.0009063885013650482, "max": 0.11517100632190705, "count": 403 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09042802080512047, "min": 0.0009063885013650482, "max": 0.11517100632190705, "count": 403 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 403 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 403 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 403 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 403 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 403 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 403 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678057211", "python_version": "3.9.16 (main, Mar 1 2023, 18:30:21) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\pa-legg\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos-v2 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.0+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1678087164" }, "total": 29952.8506473, "count": 1, "self": 0.1575236999997287, "children": { "run_training.setup": { "total": 0.1856146999999999, "count": 1, "self": 0.1856146999999999 }, "TrainerController.start_learning": { "total": 29952.507508900002, "count": 1, "self": 17.938412500770937, "children": { "TrainerController._reset_env": { "total": 5.637848499999233, "count": 42, "self": 5.637848499999233 }, "TrainerController.advance": { "total": 29928.73732699923, "count": 569807, "self": 17.51389010064304, "children": { "env_step": { "total": 12173.06392199877, "count": 569807, "self": 9406.545452299511, "children": { "SubprocessEnvManager._take_step": { "total": 2755.669963199507, "count": 569807, "self": 96.58012619973715, "children": { "TorchPolicy.evaluate": { "total": 2659.08983699977, "count": 1052256, "self": 2659.08983699977 } } }, "workers": { "total": 10.848506499750716, "count": 569807, "self": 0.0, "children": { "worker_root": { "total": 29900.837372699607, "count": 569807, "is_parallel": true, "self": 22427.73571179988, "children": { "steps_from_proto": { "total": 0.11223689999466213, "count": 84, "is_parallel": true, "self": 0.021027199979626765, "children": { "_process_rank_one_or_two_observation": { "total": 0.09120970001503537, "count": 336, "is_parallel": true, "self": 0.09120970001503537 } } }, "UnityEnvironment.step": { "total": 7472.989423999732, "count": 569807, "is_parallel": true, "self": 443.63700669922764, "children": { "UnityEnvironment._generate_step_input": { "total": 314.95180979998565, "count": 569807, "is_parallel": true, "self": 314.95180979998565 }, "communicator.exchange": { "total": 5256.4938220991025, "count": 569807, "is_parallel": true, "self": 5256.4938220991025 }, "steps_from_proto": { "total": 1457.9067854014165, "count": 1139614, "is_parallel": true, "self": 277.6322359989697, "children": { "_process_rank_one_or_two_observation": { "total": 1180.2745494024468, "count": 4558456, "is_parallel": true, "self": 1180.2745494024468 } } } } } } } } } } }, "trainer_advance": { "total": 17738.159514899817, "count": 569807, "self": 120.44777359840009, "children": { "process_trajectory": { "total": 3076.8388475014153, "count": 569807, "self": 3073.8254532014157, "children": { "RLTrainer._checkpoint": { "total": 3.013394299999618, "count": 16, "self": 3.013394299999618 } } }, "_update_policy": { "total": 14540.872893800002, "count": 404, "self": 1420.580308000075, "children": { "TorchPOCAOptimizer.update": { "total": 13120.292585799927, "count": 12110, "self": 13120.292585799927 } } } } } } }, "trainer_threads": { "total": 3.4000004234258085e-06, "count": 1, "self": 3.4000004234258085e-06 }, "TrainerController._save_models": { "total": 0.19391750000067987, "count": 1, "self": 0.006020199998602038, "children": { "RLTrainer._checkpoint": { "total": 0.18789730000207783, "count": 1, "self": 0.18789730000207783 } } } } } } }