{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4881393909454346, "min": 1.267083764076233, "max": 3.295707941055298, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31667.60546875, "min": 20720.90234375, "max": 114632.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 74.16417910447761, "min": 39.61290322580645, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19876.0, "min": 15132.0, "max": 25888.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1564.121873635981, "min": 1187.275000047532, "max": 1671.1718260434252, "count": 4982 }, "SoccerTwos.Self-play.ELO.sum": { "value": 209592.33106722147, "min": 2375.7091778662934, "max": 386157.8868361195, "count": 4982 }, "SoccerTwos.Step.mean": { "value": 49999878.0, "min": 9960.0, "max": 49999878.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999878.0, "min": 9960.0, "max": 49999878.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.008406383916735649, "min": -0.1671251356601715, "max": 0.1544373631477356, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.1264554262161255, "min": -28.875722885131836, "max": 22.500560760498047, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.006617323961108923, "min": -0.16993848979473114, "max": 0.15489326417446136, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.8867214322090149, "min": -28.25513458251953, "max": 23.072601318359375, "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": -0.19355820808837662, "min": -0.5454545454545454, "max": 0.4153510210465412, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -25.93679988384247, "min": -63.07760012149811, "max": 61.79600018262863, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.19355820808837662, "min": -0.5454545454545454, "max": 0.4153510210465412, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -25.93679988384247, "min": -63.07760012149811, "max": 61.79600018262863, "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": 0.015391487810605516, "min": 0.009520550646751265, "max": 0.02611013041653981, "count": 2423 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015391487810605516, "min": 0.009520550646751265, "max": 0.02611013041653981, "count": 2423 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08373884509007136, "min": 0.00010859680818005775, "max": 0.12758082672953605, "count": 2423 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08373884509007136, "min": 0.00010859680818005775, "max": 0.12758082672953605, "count": 2423 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08460065623124441, "min": 0.00010996900261185752, "max": 0.12996851677695911, "count": 2423 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08460065623124441, "min": 0.00010996900261185752, "max": 0.12996851677695911, "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": "1709688772", "python_version": "3.10.12 (main, Jul 5 2023, 15:34:07) [Clang 14.0.6 ]", "command_line_arguments": "/usr/local/Caskroom/miniconda/base/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1", "numpy_version": "1.23.5", "end_time_seconds": "1709977981" }, "total": 289199.275530147, "count": 1, "self": 0.5294802180142142, "children": { "run_training.setup": { "total": 0.022152472000016132, "count": 1, "self": 0.022152472000016132 }, "TrainerController.start_learning": { "total": 289198.723897457, "count": 1, "self": 62.282380895339884, "children": { "TrainerController._reset_env": { "total": 21.383551281908694, "count": 250, "self": 21.383551281908694 }, "TrainerController.advance": { "total": 289114.87745426275, "count": 3451434, "self": 57.12020782352192, "children": { "env_step": { "total": 220441.46845890585, "count": 3451434, "self": 212659.3925891547, "children": { "SubprocessEnvManager._take_step": { "total": 7742.6899995735475, "count": 3451434, "self": 311.0775826106228, "children": { "TorchPolicy.evaluate": { "total": 7431.612416962925, "count": 6281466, "self": 7431.612416962925 } } }, "workers": { "total": 39.38587017759187, "count": 3451434, "self": 0.0, "children": { "worker_root": { "total": 289093.1810051828, "count": 3451434, "is_parallel": true, "self": 83019.8263213698, "children": { "steps_from_proto": { "total": 0.4584483848675518, "count": 500, "is_parallel": true, "self": 0.09805343066022942, "children": { "_process_rank_one_or_two_observation": { "total": 0.36039495420732237, "count": 2000, "is_parallel": true, "self": 0.36039495420732237 } } }, "UnityEnvironment.step": { "total": 206072.89623542814, "count": 3451434, "is_parallel": true, "self": 604.0867641420336, "children": { "UnityEnvironment._generate_step_input": { "total": 3522.8695682702487, "count": 3451434, "is_parallel": true, "self": 3522.8695682702487 }, "communicator.exchange": { "total": 196411.9097094806, "count": 3451434, "is_parallel": true, "self": 196411.9097094806 }, "steps_from_proto": { "total": 5534.030193535267, "count": 6902868, "is_parallel": true, "self": 1007.7933321512019, "children": { "_process_rank_one_or_two_observation": { "total": 4526.236861384065, "count": 27611472, "is_parallel": true, "self": 4526.236861384065 } } } } } } } } } } }, "trainer_advance": { "total": 68616.28878753335, "count": 3451434, "self": 452.80791006171785, "children": { "process_trajectory": { "total": 8743.687690217801, "count": 3451434, "self": 8724.906973570996, "children": { "RLTrainer._checkpoint": { "total": 18.780716646805104, "count": 100, "self": 18.780716646805104 } } }, "_update_policy": { "total": 59419.79318725384, "count": 2423, "self": 5168.717389132471, "children": { "TorchPOCAOptimizer.update": { "total": 54251.07579812137, "count": 72690, "self": 54251.07579812137 } } } } } } }, "trainer_threads": { "total": 7.359776645898819e-07, "count": 1, "self": 7.359776645898819e-07 }, "TrainerController._save_models": { "total": 0.1805102810030803, "count": 1, "self": 0.00240195298101753, "children": { "RLTrainer._checkpoint": { "total": 0.17810832802206278, "count": 1, "self": 0.17810832802206278 } } } } } } }