{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.2981390953063965, "min": 2.262338161468506, "max": 3.2956650257110596, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 45815.703125, "min": 24108.728515625, "max": 142725.921875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.048780487804876, "min": 42.90350877192982, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19696.0, "min": 16392.0, "max": 23392.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1553.7855304062643, "min": 1194.1686032198077, "max": 1573.2281503741578, "count": 455 }, "SoccerTwos.Self-play.ELO.sum": { "value": 254820.82698662736, "min": 2388.4354832935755, "max": 342161.3450408545, "count": 455 }, "SoccerTwos.Step.mean": { "value": 4999920.0, "min": 9510.0, "max": 4999920.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999920.0, "min": 9510.0, "max": 4999920.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.09252378344535828, "min": -0.07063741981983185, "max": 0.15623831748962402, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 15.173900604248047, "min": -11.796449661254883, "max": 23.343124389648438, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.09287188947200775, "min": -0.06480812281370163, "max": 0.16327953338623047, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 15.230989456176758, "min": -10.822956085205078, "max": 22.875137329101562, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.2059780486473223, "min": -0.6101230766910773, "max": 0.5368454551154916, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 33.78039997816086, "min": -35.71840000152588, "max": 56.53639996051788, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.2059780486473223, "min": -0.6101230766910773, "max": 0.5368454551154916, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 33.78039997816086, "min": -35.71840000152588, "max": 56.53639996051788, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014207817256829004, "min": 0.010979171430396189, "max": 0.02400323700470229, "count": 237 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014207817256829004, "min": 0.010979171430396189, "max": 0.02400323700470229, "count": 237 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09778498858213425, "min": 6.007468935346576e-07, "max": 0.10339423318703969, "count": 237 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09778498858213425, "min": 6.007468935346576e-07, "max": 0.10339423318703969, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09948706875244777, "min": 8.445680255893725e-07, "max": 0.10556033005317052, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09948706875244777, "min": 8.445680255893725e-07, "max": 0.10556033005317052, "count": 237 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 237 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 237 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 237 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 237 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 237 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 237 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675428345", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Rishi\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1675472318" }, "total": 43974.946039200004, "count": 1, "self": 1.6476725000102306, "children": { "run_training.setup": { "total": 0.2200616000000002, "count": 1, "self": 0.2200616000000002 }, "TrainerController.start_learning": { "total": 43973.078305099996, "count": 1, "self": 14.57618140118575, "children": { "TrainerController._reset_env": { "total": 8.523469499999988, "count": 25, "self": 8.523469499999988 }, "TrainerController.advance": { "total": 43949.599182798804, "count": 332049, "self": 15.665732298330113, "children": { "env_step": { "total": 12353.305191100042, "count": 332049, "self": 9575.088284998146, "children": { "SubprocessEnvManager._take_step": { "total": 2768.4192285007684, "count": 332049, "self": 102.013348700184, "children": { "TorchPolicy.evaluate": { "total": 2666.4058798005844, "count": 637958, "self": 2666.4058798005844 } } }, "workers": { "total": 9.797677601128383, "count": 332049, "self": 0.0, "children": { "worker_root": { "total": 43944.804666598204, "count": 332049, "is_parallel": true, "self": 36240.467486498535, "children": { "steps_from_proto": { "total": 0.08914119998940606, "count": 50, "is_parallel": true, "self": 0.01767010000394542, "children": { "_process_rank_one_or_two_observation": { "total": 0.07147109998546064, "count": 200, "is_parallel": true, "self": 0.07147109998546064 } } }, "UnityEnvironment.step": { "total": 7704.248038899679, "count": 332049, "is_parallel": true, "self": 474.39904720205413, "children": { "UnityEnvironment._generate_step_input": { "total": 422.2853314968137, "count": 332049, "is_parallel": true, "self": 422.2853314968137 }, "communicator.exchange": { "total": 5244.282586198812, "count": 332049, "is_parallel": true, "self": 5244.282586198812 }, "steps_from_proto": { "total": 1563.281074001999, "count": 664098, "is_parallel": true, "self": 296.32664890037177, "children": { "_process_rank_one_or_two_observation": { "total": 1266.9544251016273, "count": 2656392, "is_parallel": true, "self": 1266.9544251016273 } } } } } } } } } } }, "trainer_advance": { "total": 31580.62825940043, "count": 332049, "self": 89.08210489978592, "children": { "process_trajectory": { "total": 12901.727697900656, "count": 332049, "self": 12898.988143900666, "children": { "RLTrainer._checkpoint": { "total": 2.739553999990676, "count": 10, "self": 2.739553999990676 } } }, "_update_policy": { "total": 18589.818456599987, "count": 237, "self": 1505.6622010002284, "children": { "TorchPOCAOptimizer.update": { "total": 17084.15625559976, "count": 7110, "self": 17084.15625559976 } } } } } } }, "trainer_threads": { "total": 1.7999991541728377e-06, "count": 1, "self": 1.7999991541728377e-06 }, "TrainerController._save_models": { "total": 0.3794696000040858, "count": 1, "self": 0.13659820000611944, "children": { "RLTrainer._checkpoint": { "total": 0.24287139999796636, "count": 1, "self": 0.24287139999796636 } } } } } } }