{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5365769863128662, "min": 1.4813590049743652, "max": 1.808916687965393, "count": 848 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30338.17578125, "min": 26535.064453125, "max": 39762.046875, "count": 848 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 72.51470588235294, "min": 44.32727272727273, "max": 96.13461538461539, "count": 848 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19724.0, "min": 17756.0, "max": 21392.0, "count": 848 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1622.0647398806539, "min": 1521.8086100971377, "max": 1629.4448554804812, "count": 848 }, "SoccerTwos.Self-play.ELO.sum": { "value": 220600.80462376893, "min": 165666.44573914562, "max": 342997.56245919503, "count": 848 }, "SoccerTwos.Step.mean": { "value": 49999973.0, "min": 41529980.0, "max": 49999973.0, "count": 848 }, "SoccerTwos.Step.sum": { "value": 49999973.0, "min": 41529980.0, "max": 49999973.0, "count": 848 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.04019450023770332, "min": -0.12426722049713135, "max": 0.07426580041646957, "count": 848 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 5.506646633148193, "min": -20.752626419067383, "max": 11.214136123657227, "count": 848 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.040437038987874985, "min": -0.12619948387145996, "max": 0.07686888426542282, "count": 848 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 5.53987455368042, "min": -21.075313568115234, "max": 11.60720157623291, "count": 848 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 848 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 848 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.14372262728475307, "min": -0.3546271589067247, "max": 0.4209885707923344, "count": 848 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 19.68999993801117, "min": -57.449599742889404, "max": 58.93839991092682, "count": 848 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.14372262728475307, "min": -0.3546271589067247, "max": 0.4209885707923344, "count": 848 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 19.68999993801117, "min": -57.449599742889404, "max": 58.93839991092682, "count": 848 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 848 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 848 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01726939525397029, "min": 0.010818473714122472, "max": 0.024776815770504376, "count": 411 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01726939525397029, "min": 0.010818473714122472, "max": 0.024776815770504376, "count": 411 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0959845520555973, "min": 0.07766435618201892, "max": 0.12066736668348313, "count": 411 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0959845520555973, "min": 0.07766435618201892, "max": 0.12066736668348313, "count": 411 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09715440968672434, "min": 0.07839207574725152, "max": 0.12248187363147736, "count": 411 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09715440968672434, "min": 0.07839207574725152, "max": 0.12248187363147736, "count": 411 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 411 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 411 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 411 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 411 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 411 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 411 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1743095433", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/home/kraz/Documents/DeepRLCourse/selfplay/VENV/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1743108821" }, "total": 13388.648106151999, "count": 1, "self": 0.31980500999816286, "children": { "run_training.setup": { "total": 0.014941138000040155, "count": 1, "self": 0.014941138000040155 }, "TrainerController.start_learning": { "total": 13388.313360004, "count": 1, "self": 7.981224752884373, "children": { "TrainerController._reset_env": { "total": 5.233504972000446, "count": 44, "self": 5.233504972000446 }, "TrainerController.advance": { "total": 13374.967367083114, "count": 584115, "self": 7.10108697205942, "children": { "env_step": { "total": 10706.45407931988, "count": 584115, "self": 8444.909337357909, "children": { "SubprocessEnvManager._take_step": { "total": 2256.47032713609, "count": 584115, "self": 44.79360782636559, "children": { "TorchPolicy.evaluate": { "total": 2211.6767193097244, "count": 1064266, "self": 2211.6767193097244 } } }, "workers": { "total": 5.07441482588024, "count": 584115, "self": 0.0, "children": { "worker_root": { "total": 13372.792390264352, "count": 584115, "is_parallel": true, "self": 5914.796352574395, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.011833296999952836, "count": 2, "is_parallel": true, "self": 0.009410772000023826, "children": { "_process_rank_one_or_two_observation": { "total": 0.00242252499992901, "count": 8, "is_parallel": true, "self": 0.00242252499992901 } } }, "UnityEnvironment.step": { "total": 0.03231245300003138, "count": 1, "is_parallel": true, "self": 0.0009449970000332542, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006791370000200914, "count": 1, "is_parallel": true, "self": 0.0006791370000200914 }, "communicator.exchange": { "total": 0.02807312200002343, "count": 1, "is_parallel": true, "self": 0.02807312200002343 }, "steps_from_proto": { "total": 0.0026151969999546054, "count": 2, "is_parallel": true, "self": 0.0004390960002638167, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021761009996907887, "count": 8, "is_parallel": true, "self": 0.0021761009996907887 } } } } } } }, "steps_from_proto": { "total": 0.10110702099120772, "count": 86, "is_parallel": true, "self": 0.016134994990238738, "children": { "_process_rank_one_or_two_observation": { "total": 0.08497202600096898, "count": 344, "is_parallel": true, "self": 0.08497202600096898 } } }, "UnityEnvironment.step": { "total": 7457.894930668966, "count": 584114, "is_parallel": true, "self": 477.0810506252719, "children": { "UnityEnvironment._generate_step_input": { "total": 306.737595483266, "count": 584114, "is_parallel": true, "self": 306.737595483266 }, "communicator.exchange": { "total": 5379.600042634662, "count": 584114, "is_parallel": true, "self": 5379.600042634662 }, "steps_from_proto": { "total": 1294.4762419257654, "count": 1168228, "is_parallel": true, "self": 208.49837002703043, "children": { "_process_rank_one_or_two_observation": { "total": 1085.977871898735, "count": 4672912, "is_parallel": true, "self": 1085.977871898735 } } } } } } } } } } }, "trainer_advance": { "total": 2661.4122007911765, "count": 584115, "self": 58.074566016771314, "children": { "process_trajectory": { "total": 1202.7350175344188, "count": 584115, "self": 1200.3584681514194, "children": { "RLTrainer._checkpoint": { "total": 2.3765493829994284, "count": 17, "self": 2.3765493829994284 } } }, "_update_policy": { "total": 1400.6026172399866, "count": 411, "self": 839.4586819019712, "children": { "TorchPOCAOptimizer.update": { "total": 561.1439353380154, "count": 12330, "self": 561.1439353380154 } } } } } } }, "trainer_threads": { "total": 6.310001481324434e-07, "count": 1, "self": 6.310001481324434e-07 }, "TrainerController._save_models": { "total": 0.13126256500072486, "count": 1, "self": 0.0018535050003265496, "children": { "RLTrainer._checkpoint": { "total": 0.1294090600003983, "count": 1, "self": 0.1294090600003983 } } } } } } }