| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 2.101013422012329, | |
| "min": 2.101013422012329, | |
| "max": 3.2957139015197754, | |
| "count": 501 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 42961.5234375, | |
| "min": 16515.8671875, | |
| "max": 152182.21875, | |
| "count": 501 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 58.142857142857146, | |
| "min": 39.3739837398374, | |
| "max": 999.0, | |
| "count": 501 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19536.0, | |
| "min": 13260.0, | |
| "max": 30128.0, | |
| "count": 501 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1542.3410988945657, | |
| "min": 1188.742219995756, | |
| "max": 1545.4246800011067, | |
| "count": 453 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 259113.30461428704, | |
| "min": 2377.484439991512, | |
| "max": 350603.1508299579, | |
| "count": 453 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 5009901.0, | |
| "min": 9084.0, | |
| "max": 5009901.0, | |
| "count": 501 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 5009901.0, | |
| "min": 9084.0, | |
| "max": 5009901.0, | |
| "count": 501 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": 0.049882616847753525, | |
| "min": -0.07383560389280319, | |
| "max": 0.18927505612373352, | |
| "count": 501 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": 8.380279541015625, | |
| "min": -12.921231269836426, | |
| "max": 25.105621337890625, | |
| "count": 501 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.0464089997112751, | |
| "min": -0.07177403569221497, | |
| "max": 0.1987553834915161, | |
| "count": 501 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 7.7967119216918945, | |
| "min": -12.824453353881836, | |
| "max": 25.68651580810547, | |
| "count": 501 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 501 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 501 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": -0.005954761235486893, | |
| "min": -0.5932400008042653, | |
| "max": 0.4941333297527198, | |
| "count": 501 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -1.000399887561798, | |
| "min": -57.321200251579285, | |
| "max": 62.83839988708496, | |
| "count": 501 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.005954761235486893, | |
| "min": -0.5932400008042653, | |
| "max": 0.4941333297527198, | |
| "count": 501 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -1.000399887561798, | |
| "min": -57.321200251579285, | |
| "max": 62.83839988708496, | |
| "count": 501 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 501 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 501 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.017983127707460276, | |
| "min": 0.011181585132483936, | |
| "max": 0.0225737148274978, | |
| "count": 239 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.017983127707460276, | |
| "min": 0.011181585132483936, | |
| "max": 0.0225737148274978, | |
| "count": 239 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.097466974457105, | |
| "min": 3.5076721758287024e-07, | |
| "max": 0.10692257781823476, | |
| "count": 239 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.097466974457105, | |
| "min": 3.5076721758287024e-07, | |
| "max": 0.10692257781823476, | |
| "count": 239 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.09892482484380404, | |
| "min": 3.649092548130284e-07, | |
| "max": 0.10853291302919388, | |
| "count": 239 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.09892482484380404, | |
| "min": 3.649092548130284e-07, | |
| "max": 0.10853291302919388, | |
| "count": 239 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 239 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 239 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 239 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 239 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 239 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005000000000000001, | |
| "min": 0.005000000000000001, | |
| "max": 0.005000000000000001, | |
| "count": 239 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1734527505", | |
| "python_version": "3.10.12 (main, Jul 5 2023, 15:34:07) [Clang 14.0.6 ]", | |
| "command_line_arguments": "/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics", | |
| "mlagents_version": "1.2.0.dev0", | |
| "mlagents_envs_version": "1.2.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.2.2", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1734608736" | |
| }, | |
| "total": 81231.475012928, | |
| "count": 1, | |
| "self": 0.18371721998846624, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.3419092809999711, | |
| "count": 1, | |
| "self": 0.3419092809999711 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 81230.949386427, | |
| "count": 1, | |
| "self": 11.902927879724302, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 14.517919049974807, | |
| "count": 26, | |
| "self": 14.517919049974807 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 81203.4898992733, | |
| "count": 337991, | |
| "self": 13.300165995155112, | |
| "children": { | |
| "env_step": { | |
| "total": 61921.089959370736, | |
| "count": 337991, | |
| "self": 59822.979835845574, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 2089.8824412134127, | |
| "count": 337991, | |
| "self": 88.97507182203117, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 2000.9073693913815, | |
| "count": 637368, | |
| "self": 2000.9073693913815 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 8.227682311749959, | |
| "count": 337991, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 81194.68807338277, | |
| "count": 337991, | |
| "is_parallel": true, | |
| "self": 22810.370800166485, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.12306323602570046, | |
| "count": 52, | |
| "is_parallel": true, | |
| "self": 0.01842242198290478, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.10464081404279568, | |
| "count": 208, | |
| "is_parallel": true, | |
| "self": 0.10464081404279568 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 58384.19420998026, | |
| "count": 337991, | |
| "is_parallel": true, | |
| "self": 165.4368085253882, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 1078.3266390013705, | |
| "count": 337991, | |
| "is_parallel": true, | |
| "self": 1078.3266390013705 | |
| }, | |
| "communicator.exchange": { | |
| "total": 55120.812672219385, | |
| "count": 337991, | |
| "is_parallel": true, | |
| "self": 55120.812672219385 | |
| }, | |
| "steps_from_proto": { | |
| "total": 2019.6180902341112, | |
| "count": 675982, | |
| "is_parallel": true, | |
| "self": 274.5357864194666, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 1745.0823038146445, | |
| "count": 2703928, | |
| "is_parallel": true, | |
| "self": 1745.0823038146445 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 19269.099773907416, | |
| "count": 337991, | |
| "self": 79.51300188005189, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 2197.717072433228, | |
| "count": 337991, | |
| "self": 2188.983380259233, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 8.733692173995223, | |
| "count": 10, | |
| "self": 8.733692173995223 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 16991.869699594135, | |
| "count": 239, | |
| "self": 995.5877852524773, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 15996.281914341658, | |
| "count": 7170, | |
| "self": 15996.281914341658 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 2.0750012481585145e-06, | |
| "count": 1, | |
| "self": 2.0750012481585145e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 1.0386381489952328, | |
| "count": 1, | |
| "self": 0.005332663000444882, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 1.0333054859947879, | |
| "count": 1, | |
| "self": 1.0333054859947879 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |