{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8325661420822144, "min": 1.8059104681015015, "max": 3.2958056926727295, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37179.1015625, "min": 27770.923828125, "max": 128205.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 50.43157894736842, "min": 40.325, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19164.0, "min": 7528.0, "max": 28852.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1503.280689634177, "min": 1201.7416295213911, "max": 1527.416259572794, "count": 482 }, "SoccerTwos.Self-play.ELO.sum": { "value": 285623.3310304936, "min": 2409.711606369081, "max": 354023.9398361049, "count": 482 }, "SoccerTwos.Step.mean": { "value": 4999995.0, "min": 9444.0, "max": 4999995.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999995.0, "min": 9444.0, "max": 4999995.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.007966858334839344, "min": -0.1157337874174118, "max": 0.26553428173065186, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.5216699838638306, "min": -20.5240478515625, "max": 46.202964782714844, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.01162212435156107, "min": -0.11689022183418274, "max": 0.2718256711959839, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.2198257446289062, "min": -20.59809112548828, "max": 47.29766845703125, "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": -0.08042722597172124, "min": -0.6875, "max": 0.44821609025714043, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -15.361600160598755, "min": -47.03439998626709, "max": 77.98959970474243, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.08042722597172124, "min": -0.6875, "max": 0.44821609025714043, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -15.361600160598755, "min": -47.03439998626709, "max": 77.98959970474243, "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": 0.021449149974311393, "min": 0.011845670055481605, "max": 0.023204468322607377, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.021449149974311393, "min": 0.011845670055481605, "max": 0.023204468322607377, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10002562354008357, "min": 1.30306451069373e-06, "max": 0.1205220880607764, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10002562354008357, "min": 1.30306451069373e-06, "max": 0.1205220880607764, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10146240095297496, "min": 1.395275902874952e-06, "max": 0.1223523552219073, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10146240095297496, "min": 1.395275902874952e-06, "max": 0.1223523552219073, "count": 239 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 239 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 239 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680089219", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\jfuentes\\AppData\\Local\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.0+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1680104782" }, "total": 15563.6206358, "count": 1, "self": 0.3488612999990437, "children": { "run_training.setup": { "total": 0.08082880000000037, "count": 1, "self": 0.08082880000000037 }, "TrainerController.start_learning": { "total": 15563.1909457, "count": 1, "self": 8.908257399874856, "children": { "TrainerController._reset_env": { "total": 4.123409599996801, "count": 25, "self": 4.123409599996801 }, "TrainerController.advance": { "total": 15549.983785900129, "count": 339110, "self": 9.25706619995799, "children": { "env_step": { "total": 5941.246636100089, "count": 339110, "self": 4608.077973100018, "children": { "SubprocessEnvManager._take_step": { "total": 1327.023943799923, "count": 339110, "self": 45.855998000080945, "children": { "TorchPolicy.evaluate": { "total": 1281.167945799842, "count": 632766, "self": 1281.167945799842 } } }, "workers": { "total": 6.144719200147295, "count": 339110, "self": 0.0, "children": { "worker_root": { "total": 15548.325803799433, "count": 339110, "is_parallel": true, "self": 11860.519040698975, "children": { "steps_from_proto": { "total": 0.03539849999106215, "count": 50, "is_parallel": true, "self": 0.007550699996119459, "children": { "_process_rank_one_or_two_observation": { "total": 0.02784779999494269, "count": 200, "is_parallel": true, "self": 0.02784779999494269 } } }, "UnityEnvironment.step": { "total": 3687.7713646004677, "count": 339110, "is_parallel": true, "self": 158.81033269967247, "children": { "UnityEnvironment._generate_step_input": { "total": 128.28108529969964, "count": 339110, "is_parallel": true, "self": 128.28108529969964 }, "communicator.exchange": { "total": 2911.5668000004944, "count": 339110, "is_parallel": true, "self": 2911.5668000004944 }, "steps_from_proto": { "total": 489.1131466006015, "count": 678220, "is_parallel": true, "self": 102.07082880097306, "children": { "_process_rank_one_or_two_observation": { "total": 387.04231779962845, "count": 2712880, "is_parallel": true, "self": 387.04231779962845 } } } } } } } } } } }, "trainer_advance": { "total": 9599.480083600081, "count": 339110, "self": 62.49121619984544, "children": { "process_trajectory": { "total": 1315.077614500242, "count": 339110, "self": 1313.4540572002418, "children": { "RLTrainer._checkpoint": { "total": 1.6235573000001295, "count": 10, "self": 1.6235573000001295 } } }, "_update_policy": { "total": 8221.911252899994, "count": 239, "self": 759.6166294999975, "children": { "TorchPOCAOptimizer.update": { "total": 7462.294623399996, "count": 7179, "self": 7462.294623399996 } } } } } } }, "trainer_threads": { "total": 1.0999992809956893e-06, "count": 1, "self": 1.0999992809956893e-06 }, "TrainerController._save_models": { "total": 0.1754916999998386, "count": 1, "self": 0.006658599999354919, "children": { "RLTrainer._checkpoint": { "total": 0.16883310000048368, "count": 1, "self": 0.16883310000048368 } } } } } } }