{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3727089166641235, "min": 1.3140296936035156, "max": 3.295708417892456, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27498.10546875, "min": 15181.9248046875, "max": 141096.8125, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.67777777777778, "min": 38.95161290322581, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19684.0, "min": 13088.0, "max": 27332.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1636.4102133046044, "min": 1199.0788229743996, "max": 1752.9235374383593, "count": 4963 }, "SoccerTwos.Self-play.ELO.sum": { "value": 294553.8383948288, "min": 2405.4962485687115, "max": 395485.79316487187, "count": 4963 }, "SoccerTwos.Step.mean": { "value": 49999798.0, "min": 9682.0, "max": 49999798.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999798.0, "min": 9682.0, "max": 49999798.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.014387241564691067, "min": -0.14452321827411652, "max": 0.1730378270149231, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 2.604090690612793, "min": -28.471073150634766, "max": 24.14034652709961, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.013612337410449982, "min": -0.14541640877723694, "max": 0.17362451553344727, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 2.4638330936431885, "min": -28.64703369140625, "max": 24.57199478149414, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.019559117641238216, "min": -0.6490666667620341, "max": 0.5342000017740897, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -3.5402002930641174, "min": -65.82560014724731, "max": 67.29599988460541, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.019559117641238216, "min": -0.6490666667620341, "max": 0.5342000017740897, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -3.5402002930641174, "min": -65.82560014724731, "max": 67.29599988460541, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01983731445943704, "min": 0.00970174377822938, "max": 0.026898910638798647, "count": 2423 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01983731445943704, "min": 0.00970174377822938, "max": 0.026898910638798647, "count": 2423 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10150654291113217, "min": 5.244935891823843e-05, "max": 0.13294473936160406, "count": 2423 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10150654291113217, "min": 5.244935891823843e-05, "max": 0.13294473936160406, "count": 2423 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10232037877043089, "min": 4.760037991218269e-05, "max": 0.1355833689371745, "count": 2423 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10232037877043089, "min": 4.760037991218269e-05, "max": 0.1355833689371745, "count": 2423 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2423 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2423 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2423 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2423 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2423 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2423 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1708762459", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:34:57) [MSC v.1936 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\s\\scoop\\persist\\mambaforge\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1708872312" }, "total": 109852.8059483, "count": 1, "self": 1.728658700012602, "children": { "run_training.setup": { "total": 0.08473060000687838, "count": 1, "self": 0.08473060000687838 }, "TrainerController.start_learning": { "total": 109850.99255899998, "count": 1, "self": 67.65651694999542, "children": { "TrainerController._reset_env": { "total": 8.078181099554058, "count": 250, "self": 8.078181099554058 }, "TrainerController.advance": { "total": 109775.12425345043, "count": 3449697, "self": 65.48773235431872, "children": { "env_step": { "total": 46783.386701313255, "count": 3449697, "self": 36225.92944563663, "children": { "SubprocessEnvManager._take_step": { "total": 10516.50654537452, "count": 3449697, "self": 342.5663258137065, "children": { "TorchPolicy.evaluate": { "total": 10173.940219560813, "count": 6283050, "self": 10173.940219560813 } } }, "workers": { "total": 40.95071030210238, "count": 3449697, "self": 0.0, "children": { "worker_root": { "total": 109765.78408021497, "count": 3449697, "is_parallel": true, "self": 80961.24994871527, "children": { "steps_from_proto": { "total": 0.3555603991262615, "count": 500, "is_parallel": true, "self": 0.07527199713513255, "children": { "_process_rank_one_or_two_observation": { "total": 0.2802884019911289, "count": 2000, "is_parallel": true, "self": 0.2802884019911289 } } }, "UnityEnvironment.step": { "total": 28804.17857110058, "count": 3449697, "is_parallel": true, "self": 1392.6681076682871, "children": { "UnityEnvironment._generate_step_input": { "total": 1054.9750639710692, "count": 3449697, "is_parallel": true, "self": 1054.9750639710692 }, "communicator.exchange": { "total": 21824.719060978445, "count": 3449697, "is_parallel": true, "self": 21824.719060978445 }, "steps_from_proto": { "total": 4531.8163384827785, "count": 6899394, "is_parallel": true, "self": 975.826527640922, "children": { "_process_rank_one_or_two_observation": { "total": 3555.9898108418565, "count": 27597576, "is_parallel": true, "self": 3555.9898108418565 } } } } } } } } } } }, "trainer_advance": { "total": 62926.24981978285, "count": 3449697, "self": 502.0779718386475, "children": { "process_trajectory": { "total": 10868.461099245527, "count": 3449697, "self": 10857.966346045258, "children": { "RLTrainer._checkpoint": { "total": 10.49475320026977, "count": 100, "self": 10.49475320026977 } } }, "_update_policy": { "total": 51555.71074869868, "count": 2423, "self": 6170.351245703176, "children": { "TorchPOCAOptimizer.update": { "total": 45385.3595029955, "count": 72690, "self": 45385.3595029955 } } } } } } }, "trainer_threads": { "total": 9.999494068324566e-07, "count": 1, "self": 9.999494068324566e-07 }, "TrainerController._save_models": { "total": 0.13360650005051866, "count": 1, "self": 0.03155570005765185, "children": { "RLTrainer._checkpoint": { "total": 0.10205079999286681, "count": 1, "self": 0.10205079999286681 } } } } } } }