{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8245843648910522, "min": 1.6784312725067139, "max": 2.265312433242798, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34389.765625, "min": 29133.91015625, "max": 49488.48046875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 89.12962962962963, "min": 39.88709677419355, "max": 112.27272727272727, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19252.0, "min": 18112.0, "max": 21080.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1559.1608573381989, "min": 1433.2700543149463, "max": 1596.7947189480517, "count": 500 }, "SoccerTwos.Self-play.ELO.sum": { "value": 168389.37259252547, "min": 132379.53545709304, "max": 368037.8036492519, "count": 500 }, "SoccerTwos.Step.mean": { "value": 9999956.0, "min": 5009949.0, "max": 9999956.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 9999956.0, "min": 5009949.0, "max": 9999956.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.06259040534496307, "min": -0.149006649851799, "max": 0.0909595862030983, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 6.759763717651367, "min": -21.009937286376953, "max": 14.35448932647705, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.06400468200445175, "min": -0.15823207795619965, "max": 0.09040261805057526, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 6.912505626678467, "min": -22.31072235107422, "max": 15.123698234558105, "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": -0.05145184971668102, "min": -0.4720098376274109, "max": 0.3441641035242977, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -5.55679976940155, "min": -58.468000054359436, "max": 40.542799949645996, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.05145184971668102, "min": -0.4720098376274109, "max": 0.3441641035242977, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -5.55679976940155, "min": -58.468000054359436, "max": 40.542799949645996, "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": 0.013097892559987183, "min": 0.010496539979552228, "max": 0.025193315698804022, "count": 242 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013097892559987183, "min": 0.010496539979552228, "max": 0.025193315698804022, "count": 242 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07199831406275431, "min": 0.06497642882168293, "max": 0.12120228086908659, "count": 242 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07199831406275431, "min": 0.06497642882168293, "max": 0.12120228086908659, "count": 242 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07323341642816862, "min": 0.06622683145105838, "max": 0.12384758914510409, "count": 242 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.07323341642816862, "min": 0.06622683145105838, "max": 0.12384758914510409, "count": 242 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 242 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 242 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 242 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 242 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 242 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 242 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717661176", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\wte42\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./results/SoccerTwos/configuration.yaml --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1717699155" }, "total": 37978.191293700016, "count": 1, "self": 1.7217363999807276, "children": { "run_training.setup": { "total": 0.1701382999890484, "count": 1, "self": 0.1701382999890484 }, "TrainerController.start_learning": { "total": 37976.299419000046, "count": 1, "self": 13.491651406046003, "children": { "TrainerController._reset_env": { "total": 12.97793160006404, "count": 26, "self": 12.97793160006404 }, "TrainerController.advance": { "total": 37949.59294379392, "count": 343208, "self": 12.36389017739566, "children": { "env_step": { "total": 12556.275907405827, "count": 343208, "self": 9485.117376446258, "children": { "SubprocessEnvManager._take_step": { "total": 3062.482253482158, "count": 343208, "self": 79.84183619933901, "children": { "TorchPolicy.evaluate": { "total": 2982.640417282819, "count": 627882, "self": 2982.640417282819 } } }, "workers": { "total": 8.676277477410622, "count": 343208, "self": 0.0, "children": { "worker_root": { "total": 37948.99914501875, "count": 343208, "is_parallel": true, "self": 30425.611817030294, "children": { "steps_from_proto": { "total": 0.09982249996392056, "count": 52, "is_parallel": true, "self": 0.018828099709935486, "children": { "_process_rank_one_or_two_observation": { "total": 0.08099440025398508, "count": 208, "is_parallel": true, "self": 0.08099440025398508 } } }, "UnityEnvironment.step": { "total": 7523.2875054884935, "count": 343208, "is_parallel": true, "self": 362.36901493981713, "children": { "UnityEnvironment._generate_step_input": { "total": 395.00273852143437, "count": 343208, "is_parallel": true, "self": 395.00273852143437 }, "communicator.exchange": { "total": 5345.40010620479, "count": 343208, "is_parallel": true, "self": 5345.40010620479 }, "steps_from_proto": { "total": 1420.515645822452, "count": 686416, "is_parallel": true, "self": 243.84451605426148, "children": { "_process_rank_one_or_two_observation": { "total": 1176.6711297681904, "count": 2745664, "is_parallel": true, "self": 1176.6711297681904 } } } } } } } } } } }, "trainer_advance": { "total": 25380.953146210697, "count": 343208, "self": 95.99636962643126, "children": { "process_trajectory": { "total": 3647.4665173835238, "count": 343208, "self": 3645.0027465834864, "children": { "RLTrainer._checkpoint": { "total": 2.4637708000373095, "count": 10, "self": 2.4637708000373095 } } }, "_update_policy": { "total": 21637.490259200742, "count": 242, "self": 1779.7197898029117, "children": { "TorchPOCAOptimizer.update": { "total": 19857.77046939783, "count": 7260, "self": 19857.77046939783 } } } } } } }, "trainer_threads": { "total": 1.9000144675374031e-06, "count": 1, "self": 1.9000144675374031e-06 }, "TrainerController._save_models": { "total": 0.23689030000241473, "count": 1, "self": 0.01592880004318431, "children": { "RLTrainer._checkpoint": { "total": 0.22096149995923042, "count": 1, "self": 0.22096149995923042 } } } } } } }