{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.821158528327942, "min": 1.7865797281265259, "max": 3.2957515716552734, "count": 784 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36073.5078125, "min": 11908.9765625, "max": 110369.0, "count": 784 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 70.05555555555556, "min": 42.6140350877193, "max": 999.0, "count": 784 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20176.0, "min": 13372.0, "max": 28728.0, "count": 784 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1651.730870948647, "min": 1194.04761563103, "max": 1661.041047044523, "count": 725 }, "SoccerTwos.Self-play.ELO.sum": { "value": 237849.24541660515, "min": 2389.598123961062, "max": 369318.25076768815, "count": 725 }, "SoccerTwos.Step.mean": { "value": 7839940.0, "min": 9384.0, "max": 7839940.0, "count": 784 }, "SoccerTwos.Step.sum": { "value": 7839940.0, "min": 9384.0, "max": 7839940.0, "count": 784 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.00606311671435833, "min": -0.11393260955810547, "max": 0.14806979894638062, "count": 784 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.8730888366699219, "min": -20.507869720458984, "max": 23.903762817382812, "count": 784 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0034142599906772375, "min": -0.11152000725269318, "max": 0.1510571390390396, "count": 784 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.4916534423828125, "min": -20.07360076904297, "max": 24.164939880371094, "count": 784 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 784 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 784 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.05976111276282205, "min": -0.5, "max": 0.4247749907275041, "count": 784 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -8.605600237846375, "min": -59.54660004377365, "max": 59.76800012588501, "count": 784 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.05976111276282205, "min": -0.5, "max": 0.4247749907275041, "count": 784 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -8.605600237846375, "min": -59.54660004377365, "max": 59.76800012588501, "count": 784 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 784 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 784 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017344167526850165, "min": 0.01151408407992373, "max": 0.024683230219913335, "count": 376 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017344167526850165, "min": 0.01151408407992373, "max": 0.024683230219913335, "count": 376 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1019140084584554, "min": 1.3814547846398759e-07, "max": 0.12279464155435563, "count": 376 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1019140084584554, "min": 1.3814547846398759e-07, "max": 0.12279464155435563, "count": 376 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10396987472971281, "min": 1.535417389675331e-07, "max": 0.12530338714520137, "count": 376 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10396987472971281, "min": 1.535417389675331e-07, "max": 0.12530338714520137, "count": 376 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 376 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 376 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 376 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 376 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 376 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 376 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1708651488", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\kenny\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1708669310" }, "total": 17821.3719575, "count": 1, "self": 2.6133588000084274, "children": { "run_training.setup": { "total": 0.15957779996097088, "count": 1, "self": 0.15957779996097088 }, "TrainerController.start_learning": { "total": 17818.59902090003, "count": 1, "self": 13.789283990859985, "children": { "TrainerController._reset_env": { "total": 12.517377799842507, "count": 40, "self": 12.517377799842507 }, "TrainerController.advance": { "total": 17792.064280409308, "count": 532414, "self": 14.279852897278033, "children": { "env_step": { "total": 13226.733587019728, "count": 532414, "self": 7462.81779612886, "children": { "SubprocessEnvManager._take_step": { "total": 5755.805586011498, "count": 532414, "self": 99.81591828144155, "children": { "TorchPolicy.evaluate": { "total": 5655.989667730057, "count": 992420, "self": 5655.989667730057 } } }, "workers": { "total": 8.110204879369121, "count": 532413, "self": 0.0, "children": { "worker_root": { "total": 17792.416428375815, "count": 532413, "is_parallel": true, "self": 11909.83916948532, "children": { "steps_from_proto": { "total": 0.07088090002071112, "count": 80, "is_parallel": true, "self": 0.014594499720260501, "children": { "_process_rank_one_or_two_observation": { "total": 0.05628640030045062, "count": 320, "is_parallel": true, "self": 0.05628640030045062 } } }, "UnityEnvironment.step": { "total": 5882.506377990474, "count": 532413, "is_parallel": true, "self": 288.9347997960285, "children": { "UnityEnvironment._generate_step_input": { "total": 218.1922739962465, "count": 532413, "is_parallel": true, "self": 218.1922739962465 }, "communicator.exchange": { "total": 4469.835122104443, "count": 532413, "is_parallel": true, "self": 4469.835122104443 }, "steps_from_proto": { "total": 905.5441820937558, "count": 1064826, "is_parallel": true, "self": 188.35595930245472, "children": { "_process_rank_one_or_two_observation": { "total": 717.1882227913011, "count": 4259304, "is_parallel": true, "self": 717.1882227913011 } } } } } } } } } } }, "trainer_advance": { "total": 4551.050840492302, "count": 532413, "self": 99.70117697620299, "children": { "process_trajectory": { "total": 2195.025824516779, "count": 532413, "self": 2191.6383199165575, "children": { "RLTrainer._checkpoint": { "total": 3.387504600221291, "count": 15, "self": 3.387504600221291 } } }, "_update_policy": { "total": 2256.3238389993203, "count": 376, "self": 1265.4843034012592, "children": { "TorchPOCAOptimizer.update": { "total": 990.839535598061, "count": 11283, "self": 990.839535598061 } } } } } } }, "trainer_threads": { "total": 1.100008375942707e-06, "count": 1, "self": 1.100008375942707e-06 }, "TrainerController._save_models": { "total": 0.22807760001160204, "count": 1, "self": 0.007860900019295514, "children": { "RLTrainer._checkpoint": { "total": 0.22021669999230653, "count": 1, "self": 0.22021669999230653 } } } } } } }