{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.2699766159057617, "min": 2.232830762863159, "max": 3.2957026958465576, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 41767.5703125, "min": 28372.73828125, "max": 110894.3203125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 403.8, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 13852.0, "max": 27860.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1204.061149742461, "min": 1195.1258727213449, "max": 1207.552417669949, "count": 108 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2408.122299484922, "min": 2391.3603685124503, "max": 14414.783627873705, "count": 108 }, "SoccerTwos.Step.mean": { "value": 4999660.0, "min": 9282.0, "max": 4999660.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999660.0, "min": 9282.0, "max": 4999660.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 2.9040646040812135e-05, "min": -0.03394120931625366, "max": 0.03186890110373497, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.00029040646040812135, "min": -0.40145978331565857, "max": 0.4142957031726837, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4253662559203804e-05, "min": -0.03666608780622482, "max": 0.02829485572874546, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.00024253662559203804, "min": -0.4280465245246887, "max": 0.36700335144996643, "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": 0.0, "min": -0.4414666652679443, "max": 0.19018461612554696, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -6.621999979019165, "max": 2.4724000096321106, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.4414666652679443, "max": 0.19018461612554696, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -6.621999979019165, "max": 2.4724000096321106, "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": 0.02023627607074256, "min": 0.009919229924465374, "max": 0.022984933798822264, "count": 228 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02023627607074256, "min": 0.009919229924465374, "max": 0.022984933798822264, "count": 228 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 4.686683456138023e-09, "min": 1.606776804200886e-09, "max": 0.006113959864402811, "count": 228 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 4.686683456138023e-09, "min": 1.606776804200886e-09, "max": 0.006113959864402811, "count": 228 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 5.256828912910313e-09, "min": 2.3889310899842067e-09, "max": 0.0061291882457832495, "count": 228 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 5.256828912910313e-09, "min": 2.3889310899842067e-09, "max": 0.0061291882457832495, "count": 228 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 228 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 228 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 228 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 228 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 228 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 228 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1720975136", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/traphole/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos-02 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1720981081" }, "total": 5945.021420411, "count": 1, "self": 0.16699708000032842, "children": { "run_training.setup": { "total": 0.006612598999936381, "count": 1, "self": 0.006612598999936381 }, "TrainerController.start_learning": { "total": 5944.847810732, "count": 1, "self": 3.611256097077785, "children": { "TrainerController._reset_env": { "total": 2.2492282200000773, "count": 25, "self": 2.2492282200000773 }, "TrainerController.advance": { "total": 5938.898799472922, "count": 325451, "self": 3.369235935994766, "children": { "env_step": { "total": 4439.669070409934, "count": 325451, "self": 3065.3949625970645, "children": { "SubprocessEnvManager._take_step": { "total": 1371.6715188837486, "count": 325451, "self": 23.89687841690602, "children": { "TorchPolicy.evaluate": { "total": 1347.7746404668426, "count": 647080, "self": 1347.7746404668426 } } }, "workers": { "total": 2.6025889291206568, "count": 325451, "self": 0.0, "children": { "worker_root": { "total": 5937.670574957921, "count": 325451, "is_parallel": true, "self": 3288.615535080862, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019549280000319413, "count": 2, "is_parallel": true, "self": 0.0009611390000827669, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009937889999491745, "count": 8, "is_parallel": true, "self": 0.0009937889999491745 } } }, "UnityEnvironment.step": { "total": 0.015712352999798895, "count": 1, "is_parallel": true, "self": 0.0002828979995683767, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020708700003524427, "count": 1, "is_parallel": true, "self": 0.00020708700003524427 }, "communicator.exchange": { "total": 0.014340580999942176, "count": 1, "is_parallel": true, "self": 0.014340580999942176 }, "steps_from_proto": { "total": 0.0008817870002530981, "count": 2, "is_parallel": true, "self": 0.00021548600034293486, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006663009999101632, "count": 8, "is_parallel": true, "self": 0.0006663009999101632 } } } } } } }, "UnityEnvironment.step": { "total": 2649.0360585360595, "count": 325450, "is_parallel": true, "self": 82.37017596480291, "children": { "UnityEnvironment._generate_step_input": { "total": 54.07778425397055, "count": 325450, "is_parallel": true, "self": 54.07778425397055 }, "communicator.exchange": { "total": 2279.225571795141, "count": 325450, "is_parallel": true, "self": 2279.225571795141 }, "steps_from_proto": { "total": 233.36252652214466, "count": 650900, "is_parallel": true, "self": 47.633744677654704, "children": { "_process_rank_one_or_two_observation": { "total": 185.72878184448996, "count": 2603600, "is_parallel": true, "self": 185.72878184448996 } } } } }, "steps_from_proto": { "total": 0.01898134099951676, "count": 48, "is_parallel": true, "self": 0.003881796998257414, "children": { "_process_rank_one_or_two_observation": { "total": 0.015099544001259346, "count": 192, "is_parallel": true, "self": 0.015099544001259346 } } } } } } } } }, "trainer_advance": { "total": 1495.860493126994, "count": 325451, "self": 36.14877145807577, "children": { "process_trajectory": { "total": 320.3251588089181, "count": 325451, "self": 319.3898621959188, "children": { "RLTrainer._checkpoint": { "total": 0.9352966129993092, "count": 10, "self": 0.9352966129993092 } } }, "_update_policy": { "total": 1139.3865628600001, "count": 228, "self": 267.03702401602345, "children": { "TorchPOCAOptimizer.update": { "total": 872.3495388439767, "count": 6849, "self": 872.3495388439767 } } } } } } }, "trainer_threads": { "total": 4.90999809699133e-07, "count": 1, "self": 4.90999809699133e-07 }, "TrainerController._save_models": { "total": 0.08852645099977963, "count": 1, "self": 0.0009331150004072697, "children": { "RLTrainer._checkpoint": { "total": 0.08759333599937236, "count": 1, "self": 0.08759333599937236 } } } } } } }