{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8962063789367676, "min": 1.8807014226913452, "max": 3.2957160472869873, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36285.8046875, "min": 10648.42578125, "max": 153698.375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 58.95238095238095, "min": 42.508620689655174, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19808.0, "min": 16216.0, "max": 24768.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1477.2705834143458, "min": 1193.0882128403377, "max": 1480.3504924990991, "count": 463 }, "SoccerTwos.Self-play.ELO.sum": { "value": 248181.45801361007, "min": 2388.4416910382383, "max": 323696.73833920876, "count": 463 }, "SoccerTwos.Step.mean": { "value": 4999958.0, "min": 9400.0, "max": 4999958.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999958.0, "min": 9400.0, "max": 4999958.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.008892318233847618, "min": -0.1019543707370758, "max": 0.1437791883945465, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.48501718044281, "min": -16.822471618652344, "max": 27.31804656982422, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.013424715958535671, "min": -0.11198695003986359, "max": 0.14580771327018738, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.2419276237487793, "min": -18.477846145629883, "max": 27.301822662353516, "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": -0.1066946126743705, "min": -0.5426250007003546, "max": 0.5336636440320448, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -17.818000316619873, "min": -54.378800213336945, "max": 60.7559996843338, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1066946126743705, "min": -0.5426250007003546, "max": 0.5336636440320448, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -17.818000316619873, "min": -54.378800213336945, "max": 60.7559996843338, "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": 0.014679395236817072, "min": 0.011399709078250452, "max": 0.02376356261665933, "count": 237 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014679395236817072, "min": 0.011399709078250452, "max": 0.02376356261665933, "count": 237 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09853155575692654, "min": 9.772455818790603e-07, "max": 0.11025716159492731, "count": 237 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09853155575692654, "min": 9.772455818790603e-07, "max": 0.11025716159492731, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10301000792533159, "min": 9.375694588698025e-07, "max": 0.11395889334380627, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10301000792533159, "min": 9.375694588698025e-07, "max": 0.11395889334380627, "count": 237 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 237 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 237 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.2, "min": 0.2, "max": 0.2, "count": 237 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.2, "min": 0.2, "max": 0.2, "count": 237 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005, "min": 0.005, "max": 0.005, "count": 237 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005, "min": 0.005, "max": 0.005, "count": 237 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1705574300", "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\\Geoff\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./ml-agents/training-envs-executables/SoccerTwos/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos-v6 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1705589184" }, "total": 14884.1766929, "count": 1, "self": 0.44374919999972917, "children": { "run_training.setup": { "total": 0.08530129999996916, "count": 1, "self": 0.08530129999996916 }, "TrainerController.start_learning": { "total": 14883.647642400001, "count": 1, "self": 8.971805899969695, "children": { "TrainerController._reset_env": { "total": 9.333892499998456, "count": 25, "self": 9.333892499998456 }, "TrainerController.advance": { "total": 14865.221567300034, "count": 336237, "self": 8.610010800326563, "children": { "env_step": { "total": 5533.360086599358, "count": 336237, "self": 4294.928082198941, "children": { "SubprocessEnvManager._take_step": { "total": 1233.2360864005047, "count": 336237, "self": 46.63843560035116, "children": { "TorchPolicy.evaluate": { "total": 1186.5976508001536, "count": 635734, "self": 1186.5976508001536 } } }, "workers": { "total": 5.19591799991133, "count": 336237, "self": 0.0, "children": { "worker_root": { "total": 14864.065335700294, "count": 336237, "is_parallel": true, "self": 11501.474056500923, "children": { "steps_from_proto": { "total": 0.039660800002479846, "count": 50, "is_parallel": true, "self": 0.008781200001521938, "children": { "_process_rank_one_or_two_observation": { "total": 0.030879600000957907, "count": 200, "is_parallel": true, "self": 0.030879600000957907 } } }, "UnityEnvironment.step": { "total": 3362.5516183993677, "count": 336237, "is_parallel": true, "self": 152.7144126003477, "children": { "UnityEnvironment._generate_step_input": { "total": 121.44532409945941, "count": 336237, "is_parallel": true, "self": 121.44532409945941 }, "communicator.exchange": { "total": 2586.6683507002663, "count": 336237, "is_parallel": true, "self": 2586.6683507002663 }, "steps_from_proto": { "total": 501.72353099929455, "count": 672474, "is_parallel": true, "self": 103.48750550001876, "children": { "_process_rank_one_or_two_observation": { "total": 398.2360254992758, "count": 2689896, "is_parallel": true, "self": 398.2360254992758 } } } } } } } } } } }, "trainer_advance": { "total": 9323.25146990035, "count": 336237, "self": 71.64440110028772, "children": { "process_trajectory": { "total": 1127.3199291000637, "count": 336237, "self": 1125.8112499000677, "children": { "RLTrainer._checkpoint": { "total": 1.5086791999960951, "count": 10, "self": 1.5086791999960951 } } }, "_update_policy": { "total": 8124.287139699998, "count": 237, "self": 973.4643128998814, "children": { "TorchPOCAOptimizer.update": { "total": 7150.822826800117, "count": 9480, "self": 7150.822826800117 } } } } } } }, "trainer_threads": { "total": 8.999995770864189e-07, "count": 1, "self": 8.999995770864189e-07 }, "TrainerController._save_models": { "total": 0.12037579999923764, "count": 1, "self": 0.0070625999996991595, "children": { "RLTrainer._checkpoint": { "total": 0.11331319999953848, "count": 1, "self": 0.11331319999953848 } } } } } } }