{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6177924871444702, "min": 1.559160590171814, "max": 3.2912204265594482, "count": 280 }, "SoccerTwos.Policy.Entropy.sum": { "value": 160485.015625, "min": 153778.0625, "max": 382624.125, "count": 280 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 71.82991202346041, "min": 51.33891213389121, "max": 834.6451612903226, "count": 280 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 97976.0, "min": 96124.0, "max": 103496.0, "count": 280 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1473.2515891224095, "min": 1194.7270440036607, "max": 1473.2515891224095, "count": 280 }, "SoccerTwos.Self-play.ELO.sum": { "value": 1004757.5837814832, "min": 21619.105691622797, "max": 1352421.8703645598, "count": 280 }, "SoccerTwos.Step.mean": { "value": 13999968.0, "min": 49040.0, "max": 13999968.0, "count": 280 }, "SoccerTwos.Step.sum": { "value": 13999968.0, "min": 49040.0, "max": 13999968.0, "count": 280 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.003308549989014864, "min": -0.0950605496764183, "max": 0.1065664067864418, "count": 280 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.259739637374878, "min": -61.84881591796875, "max": 71.85748291015625, "count": 280 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.00406001228839159, "min": -0.09523312747478485, "max": 0.10670370608568192, "count": 280 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.7729883193969727, "min": -61.80630111694336, "max": 72.01030731201172, "count": 280 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 280 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 280 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.11439531421940638, "min": -0.3210778948507811, "max": 0.18933619172863445, "count": 280 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -78.13199961185455, "min": -136.08080106973648, "max": 111.8655993938446, "count": 280 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.11439531421940638, "min": -0.3210778948507811, "max": 0.18933619172863445, "count": 280 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -78.13199961185455, "min": -136.08080106973648, "max": 111.8655993938446, "count": 280 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.025304257162497377, "min": 0.015356296338399666, "max": 0.02804526755741487, "count": 280 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.07591277148749213, "min": 0.03254546216727855, "max": 0.0806041816744255, "count": 280 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08139926840861639, "min": 0.0013327928987564518, "max": 0.10254421275522974, "count": 280 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.24419780522584916, "min": 0.0026655857975129036, "max": 0.3076326382656892, "count": 280 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08359170423613654, "min": 0.001374387451990818, "max": 0.1047428444855743, "count": 280 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.25077511270840963, "min": 0.002748774903981636, "max": 0.3142285334567229, "count": 280 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 280 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0009, "min": 0.0006, "max": 0.0009, "count": 280 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 280 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.6000000000000002, "min": 0.40000000000000013, "max": 0.6000000000000002, "count": 280 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 280 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.015000000000000003, "min": 0.010000000000000002, "max": 0.015000000000000003, "count": 280 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 280 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 280 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675540547", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:28:38) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\61404\\miniconda3\\envs\\ai-vs-ai\\Scripts\\mlagents-learn .\\config\\poca\\SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos2 --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": "1675590658" }, "total": 50110.7703753, "count": 1, "self": 0.008509400002367329, "children": { "run_training.setup": { "total": 0.11162979999999978, "count": 1, "self": 0.11162979999999978 }, "TrainerController.start_learning": { "total": 50110.6502361, "count": 1, "self": 21.424220101471292, "children": { "TrainerController._reset_env": { "total": 15.205295899985451, "count": 57, "self": 15.205295899985451 }, "TrainerController.advance": { "total": 50073.76989109855, "count": 958682, "self": 20.029607300224598, "children": { "env_step": { "total": 17271.641514498013, "count": 958682, "self": 13297.609381600512, "children": { "SubprocessEnvManager._take_step": { "total": 3959.545038996537, "count": 958682, "self": 138.8208760953912, "children": { "TorchPolicy.evaluate": { "total": 3820.724162901146, "count": 1759206, "self": 3820.724162901146 } } }, "workers": { "total": 14.487093900963043, "count": 958682, "self": 0.0, "children": { "worker_root": { "total": 50053.556540497484, "count": 958682, "is_parallel": true, "self": 39413.59898199511, "children": { "steps_from_proto": { "total": 0.10634570002497234, "count": 114, "is_parallel": true, "self": 0.01859550005252686, "children": { "_process_rank_one_or_two_observation": { "total": 0.08775019997244549, "count": 456, "is_parallel": true, "self": 0.08775019997244549 } } }, "UnityEnvironment.step": { "total": 10639.851212802354, "count": 958682, "is_parallel": true, "self": 553.0728644005721, "children": { "UnityEnvironment._generate_step_input": { "total": 713.5862827009055, "count": 958682, "is_parallel": true, "self": 713.5862827009055 }, "communicator.exchange": { "total": 7728.8221587983, "count": 958682, "is_parallel": true, "self": 7728.8221587983 }, "steps_from_proto": { "total": 1644.3699069025765, "count": 1917364, "is_parallel": true, "self": 298.9830379060609, "children": { "_process_rank_one_or_two_observation": { "total": 1345.3868689965157, "count": 7669456, "is_parallel": true, "self": 1345.3868689965157 } } } } } } } } } } }, "trainer_advance": { "total": 32782.09876930031, "count": 958682, "self": 148.05006010072248, "children": { "process_trajectory": { "total": 5153.678915599578, "count": 958682, "self": 5149.088314899587, "children": { "RLTrainer._checkpoint": { "total": 4.590600699990773, "count": 28, "self": 4.590600699990773 } } }, "_update_policy": { "total": 27480.36979360001, "count": 679, "self": 2758.50121869977, "children": { "TorchPOCAOptimizer.update": { "total": 24721.86857490024, "count": 20349, "self": 24721.86857490024 } } } } } } }, "trainer_threads": { "total": 1.0000003385357559e-06, "count": 1, "self": 1.0000003385357559e-06 }, "TrainerController._save_models": { "total": 0.25082799999654526, "count": 1, "self": 0.055095399999117944, "children": { "RLTrainer._checkpoint": { "total": 0.19573259999742731, "count": 1, "self": 0.19573259999742731 } } } } } } }