{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8848768472671509, "min": 1.8757039308547974, "max": 3.219226598739624, "count": 563 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36008.6875, "min": 2922.93212890625, "max": 112725.4453125, "count": 563 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 59.7037037037037, "min": 41.04201680672269, "max": 999.0, "count": 563 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19344.0, "min": 3996.0, "max": 31968.0, "count": 563 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 565 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 565 }, "SoccerTwos.Step.mean": { "value": 6139928.0, "min": 509710.0, "max": 6139928.0, "count": 564 }, "SoccerTwos.Step.sum": { "value": 6139928.0, "min": 509710.0, "max": 6139928.0, "count": 564 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.01574029214680195, "min": -0.1280127763748169, "max": 0.20034894347190857, "count": 564 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.549927234649658, "min": -18.177814483642578, "max": 34.25967025756836, "count": 564 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.023163100704550743, "min": -0.1331113576889038, "max": 0.2047886699438095, "count": 564 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.752422332763672, "min": -18.901813507080078, "max": 36.43235778808594, "count": 564 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 564 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 564 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.04818271707605432, "min": -0.6666666666666666, "max": 0.5627870929818, "count": 564 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -7.805600166320801, "min": -47.43999981880188, "max": 82.8496001958847, "count": 564 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.04818271707605432, "min": -0.6666666666666666, "max": 0.5627870929818, "count": 564 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -7.805600166320801, "min": -47.43999981880188, "max": 82.8496001958847, "count": 564 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1612.051858803779, "min": 1204.7975114034084, "max": 1613.035171905125, "count": 516 }, "SoccerTwos.Self-play.ELO.sum": { "value": 261152.40112621218, "min": 2409.595022806817, "max": 359929.7603653413, "count": 516 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014765378083878507, "min": 0.010268934049721186, "max": 0.023577560948130363, "count": 267 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014765378083878507, "min": 0.010268934049721186, "max": 0.023577560948130363, "count": 267 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10163015499711037, "min": 5.230705994563323e-07, "max": 0.11527040724953015, "count": 267 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10163015499711037, "min": 5.230705994563323e-07, "max": 0.11527040724953015, "count": 267 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10291009470820427, "min": 6.136595336177682e-07, "max": 0.11760621542731921, "count": 267 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10291009470820427, "min": 6.136595336177682e-07, "max": 0.11760621542731921, "count": 267 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 267 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 267 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 267 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 267 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 267 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 267 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684594638", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "F:\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/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": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1684617245" }, "total": 22607.6230215, "count": 1, "self": 0.011424199998145923, "children": { "run_training.setup": { "total": 0.10963820000000002, "count": 1, "self": 0.10963820000000002 }, "TrainerController.start_learning": { "total": 22607.501959100002, "count": 1, "self": 11.772981600068306, "children": { "TrainerController._reset_env": { "total": 4.750529199993407, "count": 30, "self": 4.750529199993407 }, "TrainerController.advance": { "total": 22590.792137599936, "count": 379103, "self": 13.231401799719606, "children": { "env_step": { "total": 9890.113025399467, "count": 379103, "self": 7852.966321599334, "children": { "SubprocessEnvManager._take_step": { "total": 2029.1959551004752, "count": 379103, "self": 73.52032779910337, "children": { "TorchPolicy.evaluate": { "total": 1955.6756273013718, "count": 716194, "self": 1955.6756273013718 } } }, "workers": { "total": 7.950748699657829, "count": 379103, "self": 0.0, "children": { "worker_root": { "total": 22567.094467499282, "count": 379103, "is_parallel": true, "self": 16198.500223798728, "children": { "steps_from_proto": { "total": 0.07193569999521987, "count": 60, "is_parallel": true, "self": 0.014546299972570509, "children": { "_process_rank_one_or_two_observation": { "total": 0.05738940002264936, "count": 240, "is_parallel": true, "self": 0.05738940002264936 } } }, "UnityEnvironment.step": { "total": 6368.522308000558, "count": 379103, "is_parallel": true, "self": 290.1131404017842, "children": { "UnityEnvironment._generate_step_input": { "total": 229.16394640028744, "count": 379103, "is_parallel": true, "self": 229.16394640028744 }, "communicator.exchange": { "total": 4896.385889898617, "count": 379103, "is_parallel": true, "self": 4896.385889898617 }, "steps_from_proto": { "total": 952.8593312998693, "count": 758206, "is_parallel": true, "self": 194.62381970201648, "children": { "_process_rank_one_or_two_observation": { "total": 758.2355115978528, "count": 3032824, "is_parallel": true, "self": 758.2355115978528 } } } } } } } } } } }, "trainer_advance": { "total": 12687.44771040075, "count": 379103, "self": 81.34807190068932, "children": { "process_trajectory": { "total": 1985.3780764000421, "count": 379103, "self": 1982.4614478000456, "children": { "RLTrainer._checkpoint": { "total": 2.916628599996592, "count": 12, "self": 2.916628599996592 } } }, "_update_policy": { "total": 10620.721562100018, "count": 268, "self": 1123.9491521999698, "children": { "TorchPOCAOptimizer.update": { "total": 9496.772409900048, "count": 8071, "self": 9496.772409900048 } } } } } } }, "trainer_threads": { "total": 2.6000016077887267e-06, "count": 1, "self": 2.6000016077887267e-06 }, "TrainerController._save_models": { "total": 0.18630810000104248, "count": 1, "self": 0.0024245000022347085, "children": { "RLTrainer._checkpoint": { "total": 0.18388359999880777, "count": 1, "self": 0.18388359999880777 } } } } } } }