{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1738739013671875, "min": 3.1062047481536865, "max": 3.295743465423584, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 57180.51171875, "min": 10395.6015625, "max": 134590.828125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 912.4, "min": 418.1666666666667, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18248.0, "min": 13464.0, "max": 28128.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1186.7506137504733, "min": 1178.8140551504239, "max": 1212.5374376786385, "count": 369 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2373.5012275009467, "min": 2357.6281103008478, "max": 26354.53280159907, "count": 369 }, "SoccerTwos.Step.mean": { "value": 4999264.0, "min": 9870.0, "max": 4999264.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999264.0, "min": 9870.0, "max": 4999264.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.006986039690673351, "min": -0.07708675414323807, "max": 0.014412983320653439, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.07684643566608429, "min": -1.0792145729064941, "max": 0.22211667895317078, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.007536457385867834, "min": -0.0770554170012474, "max": 0.014517741277813911, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.08290103077888489, "min": -1.078758955001831, "max": 0.20037278532981873, "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": 0.0787272724238309, "min": -0.5749111117588149, "max": 0.34930909221822565, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.8659999966621399, "min": -10.348400011658669, "max": 7.684800028800964, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0787272724238309, "min": -0.5749111117588149, "max": 0.34930909221822565, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.8659999966621399, "min": -10.348400011658669, "max": 7.684800028800964, "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": 0.012644073850970017, "min": 0.010785335576413976, "max": 0.023557618101282665, "count": 232 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012644073850970017, "min": 0.010785335576413976, "max": 0.023557618101282665, "count": 232 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0008207118439410503, "min": 2.665037854399088e-07, "max": 0.010205822593222062, "count": 232 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0008207118439410503, "min": 2.665037854399088e-07, "max": 0.010205822593222062, "count": 232 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0008186121189889188, "min": 2.4038172057316843e-07, "max": 0.010209519354005655, "count": 232 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0008186121189889188, "min": 2.4038172057316843e-07, "max": 0.010209519354005655, "count": 232 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 232 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 232 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 232 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 232 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 232 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 232 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1724142155", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/fortminors/miniconda3/envs/rl_course/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724144955" }, "total": 2799.289504060056, "count": 1, "self": 0.1665385509841144, "children": { "run_training.setup": { "total": 0.008161099161952734, "count": 1, "self": 0.008161099161952734 }, "TrainerController.start_learning": { "total": 2799.11480440991, "count": 1, "self": 2.449658378493041, "children": { "TrainerController._reset_env": { "total": 1.62942464184016, "count": 25, "self": 1.62942464184016 }, "TrainerController.advance": { "total": 2794.9648115821183, "count": 324971, "self": 2.392891895957291, "children": { "env_step": { "total": 2168.046913651284, "count": 324971, "self": 1635.4080960233696, "children": { "SubprocessEnvManager._take_step": { "total": 531.147889896296, "count": 324971, "self": 19.13263945421204, "children": { "TorchPolicy.evaluate": { "total": 512.0152504420839, "count": 645152, "self": 512.0152504420839 } } }, "workers": { "total": 1.4909277316182852, "count": 324971, "self": 0.0, "children": { "worker_root": { "total": 2795.6328543592244, "count": 324971, "is_parallel": true, "self": 1475.3261391385458, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010009007528424263, "count": 2, "is_parallel": true, "self": 0.00024868594482541084, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007522148080170155, "count": 8, "is_parallel": true, "self": 0.0007522148080170155 } } }, "UnityEnvironment.step": { "total": 0.011439745780080557, "count": 1, "is_parallel": true, "self": 0.00025154557079076767, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002005067653954029, "count": 1, "is_parallel": true, "self": 0.0002005067653954029 }, "communicator.exchange": { "total": 0.01031966507434845, "count": 1, "is_parallel": true, "self": 0.01031966507434845 }, "steps_from_proto": { "total": 0.0006680283695459366, "count": 2, "is_parallel": true, "self": 0.00013251090422272682, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005355174653232098, "count": 8, "is_parallel": true, "self": 0.0005355174653232098 } } } } } } }, "UnityEnvironment.step": { "total": 1320.2894980795681, "count": 324970, "is_parallel": true, "self": 75.44282341795042, "children": { "UnityEnvironment._generate_step_input": { "total": 45.88406424270943, "count": 324970, "is_parallel": true, "self": 45.88406424270943 }, "communicator.exchange": { "total": 998.7209436986595, "count": 324970, "is_parallel": true, "self": 998.7209436986595 }, "steps_from_proto": { "total": 200.24166672024876, "count": 649940, "is_parallel": true, "self": 35.716151917818934, "children": { "_process_rank_one_or_two_observation": { "total": 164.52551480242983, "count": 2599760, "is_parallel": true, "self": 164.52551480242983 } } } } }, "steps_from_proto": { "total": 0.01721714111045003, "count": 48, "is_parallel": true, "self": 0.0032692006789147854, "children": { "_process_rank_one_or_two_observation": { "total": 0.013947940431535244, "count": 192, "is_parallel": true, "self": 0.013947940431535244 } } } } } } } } }, "trainer_advance": { "total": 624.5250060348772, "count": 324971, "self": 26.96057178778574, "children": { "process_trajectory": { "total": 169.41629069950432, "count": 324971, "self": 168.63483696151525, "children": { "RLTrainer._checkpoint": { "total": 0.781453737989068, "count": 10, "self": 0.781453737989068 } } }, "_update_policy": { "total": 428.1481435475871, "count": 232, "self": 236.68582352017984, "children": { "TorchPOCAOptimizer.update": { "total": 191.46232002740726, "count": 6963, "self": 191.46232002740726 } } } } } } }, "trainer_threads": { "total": 5.052424967288971e-07, "count": 1, "self": 5.052424967288971e-07 }, "TrainerController._save_models": { "total": 0.0709093022160232, "count": 1, "self": 0.0007661245763301849, "children": { "RLTrainer._checkpoint": { "total": 0.07014317763969302, "count": 1, "self": 0.07014317763969302 } } } } } } }