{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.655691385269165, "min": 1.604853630065918, "max": 3.295750617980957, "count": 1173 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31630.328125, "min": 20975.4140625, "max": 142921.859375, "count": 1173 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 61.02469135802469, "min": 37.9453125, "max": 999.0, "count": 1173 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19772.0, "min": 15044.0, "max": 24656.0, "count": 1173 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1681.859608738653, "min": 1198.2212589071537, "max": 1697.1514042097335, "count": 1139 }, "SoccerTwos.Self-play.ELO.sum": { "value": 272461.2566156618, "min": 2397.7113664165086, "max": 420592.54139021994, "count": 1139 }, "SoccerTwos.Step.mean": { "value": 11729962.0, "min": 9346.0, "max": 11729962.0, "count": 1173 }, "SoccerTwos.Step.sum": { "value": 11729962.0, "min": 9346.0, "max": 11729962.0, "count": 1173 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.034282613545656204, "min": -0.13301002979278564, "max": 0.24164287745952606, "count": 1173 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 5.553783416748047, "min": -22.187185287475586, "max": 33.346717834472656, "count": 1173 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.03710721433162689, "min": -0.13044849038124084, "max": 0.23275840282440186, "count": 1173 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 6.011368751525879, "min": -22.110445022583008, "max": 32.12065887451172, "count": 1173 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1173 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1173 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.24103456882782925, "min": -0.6153846153846154, "max": 0.5917623189912327, "count": 1173 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 39.04760015010834, "min": -60.84120035171509, "max": 81.6632000207901, "count": 1173 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.24103456882782925, "min": -0.6153846153846154, "max": 0.5917623189912327, "count": 1173 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 39.04760015010834, "min": -60.84120035171509, "max": 81.6632000207901, "count": 1173 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1173 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1173 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.012525795083274716, "min": 0.010618784060837546, "max": 0.024950614649181566, "count": 565 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012525795083274716, "min": 0.010618784060837546, "max": 0.024950614649181566, "count": 565 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11439260989427566, "min": 9.553729917873473e-06, "max": 0.12423499897122384, "count": 565 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11439260989427566, "min": 9.553729917873473e-06, "max": 0.12423499897122384, "count": 565 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11647900144259135, "min": 1.1408822880791073e-05, "max": 0.12736859222253163, "count": 565 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11647900144259135, "min": 1.1408822880791073e-05, "max": 0.12736859222253163, "count": 565 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 565 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 565 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 565 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 565 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 565 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 565 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1696097243", "python_version": "3.9.18 (main, Sep 11 2023, 14:09:26) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\F:\\Anaconda3\\envs\\protonh-rl1\\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": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1696129105" }, "total": 31862.466951500002, "count": 1, "self": 2.511634000002232, "children": { "run_training.setup": { "total": 0.11477240000000055, "count": 1, "self": 0.11477240000000055 }, "TrainerController.start_learning": { "total": 31859.8405451, "count": 1, "self": 17.501605399760592, "children": { "TrainerController._reset_env": { "total": 7.557385799996531, "count": 40, "self": 7.557385799996531 }, "TrainerController.advance": { "total": 31834.661665400246, "count": 800682, "self": 17.35468059842242, "children": { "env_step": { "total": 12246.201269702273, "count": 800682, "self": 9710.239232002055, "children": { "SubprocessEnvManager._take_step": { "total": 2524.520591000684, "count": 800682, "self": 93.15535820083278, "children": { "TorchPolicy.evaluate": { "total": 2431.365232799851, "count": 1476658, "self": 2431.365232799851 } } }, "workers": { "total": 11.441446699534, "count": 800681, "self": 0.0, "children": { "worker_root": { "total": 31829.852516000356, "count": 800681, "is_parallel": true, "self": 24080.85557060062, "children": { "steps_from_proto": { "total": 0.05577380000377907, "count": 80, "is_parallel": true, "self": 0.012069000011796227, "children": { "_process_rank_one_or_two_observation": { "total": 0.043704799991982846, "count": 320, "is_parallel": true, "self": 0.043704799991982846 } } }, "UnityEnvironment.step": { "total": 7748.941171599733, "count": 800681, "is_parallel": true, "self": 375.85933039860447, "children": { "UnityEnvironment._generate_step_input": { "total": 333.253516900041, "count": 800681, "is_parallel": true, "self": 333.253516900041 }, "communicator.exchange": { "total": 5818.657158099784, "count": 800681, "is_parallel": true, "self": 5818.657158099784 }, "steps_from_proto": { "total": 1221.171166201303, "count": 1601362, "is_parallel": true, "self": 260.5219661058833, "children": { "_process_rank_one_or_two_observation": { "total": 960.6492000954198, "count": 6405448, "is_parallel": true, "self": 960.6492000954198 } } } } } } } } } } }, "trainer_advance": { "total": 19571.10571509955, "count": 800681, "self": 133.16959149865943, "children": { "process_trajectory": { "total": 3299.218758000864, "count": 800681, "self": 3291.8554653008587, "children": { "RLTrainer._checkpoint": { "total": 7.363292700005559, "count": 23, "self": 7.363292700005559 } } }, "_update_policy": { "total": 16138.717365600029, "count": 565, "self": 1609.4895082000457, "children": { "TorchPOCAOptimizer.update": { "total": 14529.227857399983, "count": 16950, "self": 14529.227857399983 } } } } } } }, "trainer_threads": { "total": 1.3999997463542968e-06, "count": 1, "self": 1.3999997463542968e-06 }, "TrainerController._save_models": { "total": 0.11988709999786806, "count": 1, "self": 0.0069741999977850355, "children": { "RLTrainer._checkpoint": { "total": 0.11291290000008303, "count": 1, "self": 0.11291290000008303 } } } } } } }