{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5572160482406616, "min": 1.4796764850616455, "max": 2.316222667694092, "count": 692 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32439.92578125, "min": 19549.421875, "max": 51443.2890625, "count": 692 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.79012345679013, "min": 37.40816326530612, "max": 112.68888888888888, "count": 692 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19696.0, "min": 7332.0, "max": 20892.0, "count": 692 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1532.850168432362, "min": 1393.8570641808913, "max": 1556.063024196752, "count": 692 }, "SoccerTwos.Self-play.ELO.sum": { "value": 248321.72728604265, "min": 136472.0477161022, "max": 363256.00183768506, "count": 692 }, "SoccerTwos.Step.mean": { "value": 10159890.0, "min": 3249918.0, "max": 10159890.0, "count": 692 }, "SoccerTwos.Step.sum": { "value": 10159890.0, "min": 3249918.0, "max": 10159890.0, "count": 692 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.017411012202501297, "min": -0.11417428404092789, "max": 0.15166069567203522, "count": 692 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.8031728267669678, "min": -22.35116958618164, "max": 24.698177337646484, "count": 692 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.021648546680808067, "min": -0.11651396751403809, "max": 0.1547374129295349, "count": 692 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.4854159355163574, "min": -22.662694931030273, "max": 25.887794494628906, "count": 692 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 692 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 692 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.08805714334760394, "min": -0.31483267262430475, "max": 0.3760611441484682, "count": 692 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -14.177200078964233, "min": -66.06939989328384, "max": 63.40679979324341, "count": 692 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.08805714334760394, "min": -0.31483267262430475, "max": 0.3760611441484682, "count": 692 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -14.177200078964233, "min": -66.06939989328384, "max": 63.40679979324341, "count": 692 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 692 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 692 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019116126811907937, "min": 0.009264162741116404, "max": 0.023554403986781835, "count": 335 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019116126811907937, "min": 0.009264162741116404, "max": 0.023554403986781835, "count": 335 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10319636215766272, "min": 0.07646674041946729, "max": 0.1312625450392564, "count": 335 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10319636215766272, "min": 0.07646674041946729, "max": 0.1312625450392564, "count": 335 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10433849568168323, "min": 0.07763358304897944, "max": 0.13379605958859125, "count": 335 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10433849568168323, "min": 0.07763358304897944, "max": 0.13379605958859125, "count": 335 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 335 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 335 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 335 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 335 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 335 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 335 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1685467254", "python_version": "3.9.16 (main, Mar 8 2023, 04:29:24) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/cmpatino/Software/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1685492584" }, "total": 24436.345536667002, "count": 1, "self": 0.29455254100321326, "children": { "run_training.setup": { "total": 0.013618209000000103, "count": 1, "self": 0.013618209000000103 }, "TrainerController.start_learning": { "total": 24436.037365917, "count": 1, "self": 5.864208124992729, "children": { "TrainerController._reset_env": { "total": 2.8453661679947158, "count": 36, "self": 2.8453661679947158 }, "TrainerController.advance": { "total": 24427.21861583201, "count": 483364, "self": 5.138009383848839, "children": { "env_step": { "total": 18952.890719426316, "count": 483364, "self": 18194.754368307887, "children": { "SubprocessEnvManager._take_step": { "total": 754.6493575943163, "count": 483364, "self": 20.78563564614217, "children": { "TorchPolicy.evaluate": { "total": 733.8637219481741, "count": 867500, "self": 733.8637219481741 } } }, "workers": { "total": 3.4869935241127905, "count": 483363, "self": 0.0, "children": { "worker_root": { "total": 24425.90537473736, "count": 483363, "is_parallel": true, "self": 6859.6228179850405, "children": { "steps_from_proto": { "total": 0.054453288007503264, "count": 72, "is_parallel": true, "self": 0.00580904101556956, "children": { "_process_rank_one_or_two_observation": { "total": 0.048644246991933704, "count": 288, "is_parallel": true, "self": 0.048644246991933704 } } }, "UnityEnvironment.step": { "total": 17566.22810346431, "count": 483363, "is_parallel": true, "self": 50.10850966785438, "children": { "UnityEnvironment._generate_step_input": { "total": 318.4643417006471, "count": 483363, "is_parallel": true, "self": 318.4643417006471 }, "communicator.exchange": { "total": 16486.666769027204, "count": 483363, "is_parallel": true, "self": 16486.666769027204 }, "steps_from_proto": { "total": 710.988483068601, "count": 966726, "is_parallel": true, "self": 75.7151926292131, "children": { "_process_rank_one_or_two_observation": { "total": 635.2732904393879, "count": 3866904, "is_parallel": true, "self": 635.2732904393879 } } } } } } } } } } }, "trainer_advance": { "total": 5469.1898870218465, "count": 483363, "self": 38.61935983038529, "children": { "process_trajectory": { "total": 1201.0461626584283, "count": 483363, "self": 1199.561214450426, "children": { "RLTrainer._checkpoint": { "total": 1.484948208002379, "count": 14, "self": 1.484948208002379 } } }, "_update_policy": { "total": 4229.524364533033, "count": 336, "self": 530.0860378200996, "children": { "TorchPOCAOptimizer.update": { "total": 3699.4383267129333, "count": 10080, "self": 3699.4383267129333 } } } } } } }, "trainer_threads": { "total": 4.169996827840805e-07, "count": 1, "self": 4.169996827840805e-07 }, "TrainerController._save_models": { "total": 0.1091753750006319, "count": 1, "self": 0.0029110840005159844, "children": { "RLTrainer._checkpoint": { "total": 0.10626429100011592, "count": 1, "self": 0.10626429100011592 } } } } } } }