{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8118613958358765, "min": 1.6636101007461548, "max": 1.843156099319458, "count": 138 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34613.80078125, "min": 31359.28515625, "max": 39437.20703125, "count": 138 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.15217391304348, "min": 44.61818181818182, "max": 74.35820895522389, "count": 138 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19928.0, "min": 16656.0, "max": 20384.0, "count": 138 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1702.4857863511247, "min": 1689.0574729382788, "max": 1741.4789908541304, "count": 138 }, "SoccerTwos.Self-play.ELO.sum": { "value": 313257.38468860695, "min": 230337.3248480296, "max": 374924.64448671497, "count": 138 }, "SoccerTwos.Step.mean": { "value": 10009980.0, "min": 8639960.0, "max": 10009980.0, "count": 138 }, "SoccerTwos.Step.sum": { "value": 10009980.0, "min": 8639960.0, "max": 10009980.0, "count": 138 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.010594820603728294, "min": -0.09363055974245071, "max": 0.06854648143053055, "count": 138 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.9388521909713745, "min": -18.35158920288086, "max": 13.549934387207031, "count": 138 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.012300742790102959, "min": -0.09186331927776337, "max": 0.07186656445264816, "count": 138 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.2510359287261963, "min": -18.005210876464844, "max": 15.093283653259277, "count": 138 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 138 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 138 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.009724591599136103, "min": -0.30681618445181436, "max": 0.25714331578443395, "count": 138 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.7796002626419067, "min": -53.515599727630615, "max": 50.4333997964859, "count": 138 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.009724591599136103, "min": -0.30681618445181436, "max": 0.25714331578443395, "count": 138 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.7796002626419067, "min": -53.515599727630615, "max": 50.4333997964859, "count": 138 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 138 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 138 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019012902875935347, "min": 0.010337586479363382, "max": 0.02299332935363054, "count": 66 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019012902875935347, "min": 0.010337586479363382, "max": 0.02299332935363054, "count": 66 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10139179453253747, "min": 0.09779081518451373, "max": 0.12342411826054255, "count": 66 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10139179453253747, "min": 0.09779081518451373, "max": 0.12342411826054255, "count": 66 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10178855781753858, "min": 0.09808570270737012, "max": 0.12474122320612271, "count": 66 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10178855781753858, "min": 0.09808570270737012, "max": 0.12474122320612271, "count": 66 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00015, "min": 0.00015, "max": 0.00015, "count": 66 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00015, "min": 0.00015, "max": 0.00015, "count": 66 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 66 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 66 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 66 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 66 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678726861", "python_version": "3.9.5 (tags/v3.9.5:0a7dcbd, May 3 2021, 17:27:52) [MSC v.1928 64 bit (AMD64)]", "command_line_arguments": "D:\\Documents\\Tesis\\thesis_env\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cu117", "numpy_version": "1.21.2", "end_time_seconds": "1678728868" }, "total": 2007.3160672, "count": 1, "self": 0.056033299999853625, "children": { "run_training.setup": { "total": 0.08213850000000011, "count": 1, "self": 0.08213850000000011 }, "TrainerController.start_learning": { "total": 2007.1778954000001, "count": 1, "self": 1.637189700020599, "children": { "TrainerController._reset_env": { "total": 4.090669199999826, "count": 8, "self": 4.090669199999826 }, "TrainerController.advance": { "total": 2001.3126216999794, "count": 96197, "self": 1.4328627999125274, "children": { "env_step": { "total": 1407.015403500059, "count": 96197, "self": 788.8511395001028, "children": { "SubprocessEnvManager._take_step": { "total": 617.252432499953, "count": 96197, "self": 8.982159299974114, "children": { "TorchPolicy.evaluate": { "total": 608.2702731999789, "count": 172776, "self": 608.2702731999789 } } }, "workers": { "total": 0.9118315000031885, "count": 96197, "self": 0.0, "children": { "worker_root": { "total": 1998.0237361000184, "count": 96197, "is_parallel": true, "self": 1365.5229779000274, "children": { "steps_from_proto": { "total": 0.010172899999911778, "count": 16, "is_parallel": true, "self": 0.00204889999975455, "children": { "_process_rank_one_or_two_observation": { "total": 0.008124000000157228, "count": 64, "is_parallel": true, "self": 0.008124000000157228 } } }, "UnityEnvironment.step": { "total": 632.4905852999909, "count": 96197, "is_parallel": true, "self": 35.8199392999702, "children": { "UnityEnvironment._generate_step_input": { "total": 25.812671299991184, "count": 96197, "is_parallel": true, "self": 25.812671299991184 }, "communicator.exchange": { "total": 465.90249760001274, "count": 96197, "is_parallel": true, "self": 465.90249760001274 }, "steps_from_proto": { "total": 104.95547710001682, "count": 192394, "is_parallel": true, "self": 21.353446499925468, "children": { "_process_rank_one_or_two_observation": { "total": 83.60203060009135, "count": 769576, "is_parallel": true, "self": 83.60203060009135 } } } } } } } } } } }, "trainer_advance": { "total": 592.864355400008, "count": 96197, "self": 12.526563400013629, "children": { "process_trajectory": { "total": 312.0778004999946, "count": 96197, "self": 311.60571909999476, "children": { "RLTrainer._checkpoint": { "total": 0.4720813999998654, "count": 3, "self": 0.4720813999998654 } } }, "_update_policy": { "total": 268.2599914999998, "count": 67, "self": 141.44559800000098, "children": { "TorchPOCAOptimizer.update": { "total": 126.81439349999879, "count": 2007, "self": 126.81439349999879 } } } } } } }, "trainer_threads": { "total": 6.000000212225132e-07, "count": 1, "self": 6.000000212225132e-07 }, "TrainerController._save_models": { "total": 0.1374142000001939, "count": 1, "self": 0.0266540000002351, "children": { "RLTrainer._checkpoint": { "total": 0.11076019999995879, "count": 1, "self": 0.11076019999995879 } } } } } } }