{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.276331901550293, "min": 3.2658324241638184, "max": 3.2957749366760254, "count": 8650 }, "SoccerTwos.Policy.Entropy.sum": { "value": 10484.26171875, "min": 104.81745910644531, "max": 15789.125, "count": 8650 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 158.5, "min": 0.0, "max": 999.0, "count": 2652 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 1268.0, "min": 0.0, "max": 19980.0, "count": 2652 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1164.2205715235966, "min": 1159.2077927993414, "max": 1204.7435239037027, "count": 1051 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2328.4411430471932, "min": 2318.885447365601, "max": 7116.464726252681, "count": 1051 }, "SoccerTwos.Step.mean": { "value": 4999966.0, "min": 458.0, "max": 4999966.0, "count": 10000 }, "SoccerTwos.Step.sum": { "value": 4999966.0, "min": 458.0, "max": 4999966.0, "count": 10000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.017738109454512596, "min": -0.30164986848831177, "max": 0.03233775869011879, "count": 10000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.08869054913520813, "min": -1.8090074062347412, "max": 0.19402655959129333, "count": 10000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.01838485710322857, "min": -0.30160006880760193, "max": 0.033794302493333817, "count": 10000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.091924287378788, "min": -1.8077348470687866, "max": 0.19572553038597107, "count": 10000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2987 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2987 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.5, "min": -1.0, "max": 0.9711999893188477, "count": 2987 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.0, "min": -4.0, "max": 4.129000008106232, "count": 2987 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.5, "min": -1.0, "max": 0.9711999893188477, "count": 2987 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.0, "min": -4.0, "max": 4.129000008106232, "count": 2987 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.07197124875065955, "min": 0.016312858080849625, "max": 0.09011630510742014, "count": 1783 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.07197124875065955, "min": 0.016312858080849625, "max": 0.09011630510742014, "count": 1783 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 2.1567379421453964e-05, "min": 2.608480258459167e-06, "max": 0.02774455361068249, "count": 1783 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 2.1567379421453964e-05, "min": 2.608480258459167e-06, "max": 0.02774455361068249, "count": 1783 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 1.626949779165443e-05, "min": 2.6999044848707854e-06, "max": 0.027782930806279183, "count": 1783 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 1.626949779165443e-05, "min": 2.6999044848707854e-06, "max": 0.027782930806279183, "count": 1783 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 2.5e-05, "min": 2.5e-05, "max": 2.5000000000000005e-05, "count": 1783 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 2.5e-05, "min": 2.5e-05, "max": 2.5000000000000005e-05, "count": 1783 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.2, "min": 0.2, "max": 0.20000000000000007, "count": 1783 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.2, "min": 0.2, "max": 0.20000000000000007, "count": 1783 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.004999999999999999, "min": 0.004999999999999999, "max": 0.005, "count": 1783 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.004999999999999999, "min": 0.004999999999999999, "max": 0.005, "count": 1783 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687852430", "python_version": "3.10.2 (tags/v3.10.2:a58ebcc, Jan 17 2022, 14:12:15) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\MaiDo\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/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": "1.12.1+cpu", "numpy_version": "1.23.4", "end_time_seconds": "1687861892" }, "total": 9462.54121310002, "count": 1, "self": 0.36523850000230595, "children": { "run_training.setup": { "total": 0.10421369998948649, "count": 1, "self": 0.10421369998948649 }, "TrainerController.start_learning": { "total": 9462.071760900028, "count": 1, "self": 9.755972094717436, "children": { "TrainerController._reset_env": { "total": 9.259877300064545, "count": 200, "self": 9.259877300064545 }, "TrainerController.advance": { "total": 9442.898137405224, "count": 323130, "self": 9.681490987772122, "children": { "env_step": { "total": 7450.867933301255, "count": 323130, "self": 6143.621739796363, "children": { "SubprocessEnvManager._take_step": { "total": 1300.730649602483, "count": 323130, "self": 55.70470830902923, "children": { "TorchPolicy.evaluate": { "total": 1245.0259412934538, "count": 641272, "self": 1245.0259412934538 } } }, "workers": { "total": 6.515543902409263, "count": 323130, "self": 0.0, "children": { "worker_root": { "total": 9444.722208496823, "count": 323130, "is_parallel": true, "self": 4412.559179384203, "children": { "steps_from_proto": { "total": 0.44778919965028763, "count": 400, "is_parallel": true, "self": 0.0883305004099384, "children": { "_process_rank_one_or_two_observation": { "total": 0.35945869924034923, "count": 1600, "is_parallel": true, "self": 0.35945869924034923 } } }, "UnityEnvironment.step": { "total": 5031.71523991297, "count": 323130, "is_parallel": true, "self": 244.5766650448204, "children": { "UnityEnvironment._generate_step_input": { "total": 184.72282387921587, "count": 323130, "is_parallel": true, "self": 184.72282387921587 }, "communicator.exchange": { "total": 3853.434067182534, "count": 323130, "is_parallel": true, "self": 3853.434067182534 }, "steps_from_proto": { "total": 748.9816838063998, "count": 646260, "is_parallel": true, "self": 142.99139347008895, "children": { "_process_rank_one_or_two_observation": { "total": 605.9902903363109, "count": 2585040, "is_parallel": true, "self": 605.9902903363109 } } } } } } } } } } }, "trainer_advance": { "total": 1982.3487131161964, "count": 323130, "self": 75.70392960589379, "children": { "process_trajectory": { "total": 1011.022233310272, "count": 323130, "self": 1008.8699188103201, "children": { "RLTrainer._checkpoint": { "total": 2.152314499951899, "count": 10, "self": 2.152314499951899 } } }, "_update_policy": { "total": 895.6225502000307, "count": 1783, "self": 307.28713700175285, "children": { "TorchPOCAOptimizer.update": { "total": 588.3354131982778, "count": 18880, "self": 588.3354131982778 } } } } } } }, "trainer_threads": { "total": 9.00006853044033e-07, "count": 1, "self": 9.00006853044033e-07 }, "TrainerController._save_models": { "total": 0.15777320001507178, "count": 1, "self": 0.004239100031554699, "children": { "RLTrainer._checkpoint": { "total": 0.15353409998351708, "count": 1, "self": 0.15353409998351708 } } } } } } }