{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.346792697906494, "min": 2.2970592975616455, "max": 2.388735294342041, "count": 299 }, "SoccerTwos.Policy.Entropy.sum": { "value": 45208.61328125, "min": 37882.7109375, "max": 60526.88671875, "count": 299 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 68.73239436619718, "min": 47.45631067961165, "max": 103.39583333333333, "count": 299 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19520.0, "min": 18124.0, "max": 21048.0, "count": 299 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1586.2263956757824, "min": 1552.918132508456, "max": 1615.7520349913696, "count": 299 }, "SoccerTwos.Self-play.ELO.sum": { "value": 225244.1481859611, "min": 153773.3202231244, "max": 326572.3715284068, "count": 299 }, "SoccerTwos.Step.mean": { "value": 49999997.0, "min": 47019979.0, "max": 49999997.0, "count": 299 }, "SoccerTwos.Step.sum": { "value": 49999997.0, "min": 47019979.0, "max": 49999997.0, "count": 299 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.06248742341995239, "min": -0.1325869858264923, "max": 0.06702996790409088, "count": 299 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -8.935701370239258, "min": -22.93754768371582, "max": 9.920434951782227, "count": 299 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0648917406797409, "min": -0.13301512598991394, "max": 0.06738097965717316, "count": 299 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -9.279519081115723, "min": -23.011615753173828, "max": 9.97238540649414, "count": 299 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 299 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 299 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.16381818181151278, "min": -0.4128225345007131, "max": 0.28632461382792546, "count": 299 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -23.425999999046326, "min": -58.62079989910126, "max": 37.22219979763031, "count": 299 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.16381818181151278, "min": -0.4128225345007131, "max": 0.28632461382792546, "count": 299 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -23.425999999046326, "min": -58.62079989910126, "max": 37.22219979763031, "count": 299 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 299 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 299 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.0162993732917433, "min": 0.011969914202442549, "max": 0.02426063035527477, "count": 145 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0162993732917433, "min": 0.011969914202442549, "max": 0.02426063035527477, "count": 145 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08963213935494423, "min": 0.07290808036923409, "max": 0.10371330976486207, "count": 145 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08963213935494423, "min": 0.07290808036923409, "max": 0.10371330976486207, "count": 145 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09066422507166863, "min": 0.07393495415647824, "max": 0.1055140865345796, "count": 145 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09066422507166863, "min": 0.07393495415647824, "max": 0.1055140865345796, "count": 145 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 145 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 145 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 145 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 145 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.010000000000000002, "min": 0.010000000000000002, "max": 0.010000000000000002, "count": 145 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.010000000000000002, "min": 0.010000000000000002, "max": 0.010000000000000002, "count": 145 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677301169", "python_version": "3.8.16 (default, Jan 17 2023, 22:25:28) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Kaush\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=pocatrainergoalbeta --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": "1677308435" }, "total": 7265.1654886, "count": 1, "self": 0.5663734999989174, "children": { "run_training.setup": { "total": 0.09132439999999997, "count": 1, "self": 0.09132439999999997 }, "TrainerController.start_learning": { "total": 7264.5077907, "count": 1, "self": 5.734095199890362, "children": { "TrainerController._reset_env": { "total": 11.90960289999987, "count": 16, "self": 11.90960289999987 }, "TrainerController.advance": { "total": 7246.6439557001095, "count": 204663, "self": 5.8572592001864905, "children": { "env_step": { "total": 4941.387445299964, "count": 204663, "self": 2565.2636788999193, "children": { "SubprocessEnvManager._take_step": { "total": 2372.7986070000015, "count": 204663, "self": 33.9239966001046, "children": { "TorchPolicy.evaluate": { "total": 2338.874610399897, "count": 375166, "self": 2338.874610399897 } } }, "workers": { "total": 3.3251594000436278, "count": 204663, "self": 0.0, "children": { "worker_root": { "total": 7247.896646600133, "count": 204663, "is_parallel": true, "self": 5254.661512699902, "children": { "steps_from_proto": { "total": 0.029863900001497967, "count": 32, "is_parallel": true, "self": 0.00693150000241971, "children": { "_process_rank_one_or_two_observation": { "total": 0.022932399999078257, "count": 128, "is_parallel": true, "self": 0.022932399999078257 } } }, "UnityEnvironment.step": { "total": 1993.2052700002291, "count": 204663, "is_parallel": true, "self": 101.57907880004905, "children": { "UnityEnvironment._generate_step_input": { "total": 101.0035848999301, "count": 204663, "is_parallel": true, "self": 101.0035848999301 }, "communicator.exchange": { "total": 1473.9688821001653, "count": 204663, "is_parallel": true, "self": 1473.9688821001653 }, "steps_from_proto": { "total": 316.65372420008464, "count": 409326, "is_parallel": true, "self": 68.79668929965652, "children": { "_process_rank_one_or_two_observation": { "total": 247.85703490042812, "count": 1637304, "is_parallel": true, "self": 247.85703490042812 } } } } } } } } } } }, "trainer_advance": { "total": 2299.399251199959, "count": 204663, "self": 36.0268705999124, "children": { "process_trajectory": { "total": 1061.7885868000433, "count": 204663, "self": 1060.3413790000432, "children": { "RLTrainer._checkpoint": { "total": 1.447207800000001, "count": 6, "self": 1.447207800000001 } } }, "_update_policy": { "total": 1201.5837938000034, "count": 145, "self": 635.6391238000203, "children": { "TorchPOCAOptimizer.update": { "total": 565.944669999983, "count": 4350, "self": 565.944669999983 } } } } } } }, "trainer_threads": { "total": 3.6999999792897142e-06, "count": 1, "self": 3.6999999792897142e-06 }, "TrainerController._save_models": { "total": 0.22013320000041858, "count": 1, "self": 0.0033798000004026107, "children": { "RLTrainer._checkpoint": { "total": 0.21675340000001597, "count": 1, "self": 0.21675340000001597 } } } } } } }