{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1914870738983154, "min": 3.125495195388794, "max": 3.2957162857055664, "count": 200 }, "SoccerTwos.Policy.Entropy.sum": { "value": 85072.28125, "min": 21063.49609375, "max": 131480.6875, "count": 200 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 826.8333333333334, "min": 381.45454545454544, "max": 999.0, "count": 200 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19844.0, "min": 10176.0, "max": 30304.0, "count": 200 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1199.260041459385, "min": 1190.478149851216, "max": 1199.4077989637335, "count": 147 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4797.04016583754, "min": 2380.956299702432, "max": 14376.351177542456, "count": 147 }, "SoccerTwos.Step.mean": { "value": 1999816.0, "min": 9168.0, "max": 1999816.0, "count": 200 }, "SoccerTwos.Step.sum": { "value": 1999816.0, "min": 9168.0, "max": 1999816.0, "count": 200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.014473618008196354, "min": -0.09719818830490112, "max": 0.005388463381677866, "count": 200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.17368341982364655, "min": -1.6523691415786743, "max": 0.05927309766411781, "count": 200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.014098864048719406, "min": -0.09718871116638184, "max": 0.006647351663559675, "count": 200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.16918636858463287, "min": -1.6521615982055664, "max": 0.07976821810007095, "count": 200 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.25, "min": -0.6153846153846154, "max": 0.3363714303289141, "count": 200 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -3.0, "min": -8.0, "max": 4.709200024604797, "count": 200 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.25, "min": -0.6153846153846154, "max": 0.3363714303289141, "count": 200 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -3.0, "min": -8.0, "max": 4.709200024604797, "count": 200 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016371077149233314, "min": 0.011968172658816912, "max": 0.02205759734691431, "count": 92 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016371077149233314, "min": 0.011968172658816912, "max": 0.02205759734691431, "count": 92 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0006172636848835585, "min": 2.997778862360671e-06, "max": 0.005579765963678558, "count": 92 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0006172636848835585, "min": 2.997778862360671e-06, "max": 0.005579765963678558, "count": 92 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0006175495499822621, "min": 2.9111422842712877e-06, "max": 0.005300766710812847, "count": 92 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0006175495499822621, "min": 2.9111422842712877e-06, "max": 0.005300766710812847, "count": 92 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 92 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 92 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 92 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 92 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 92 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 92 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1707246301", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos --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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707250627" }, "total": 4325.935028147001, "count": 1, "self": 0.4497174080015611, "children": { "run_training.setup": { "total": 0.0824290729999575, "count": 1, "self": 0.0824290729999575 }, "TrainerController.start_learning": { "total": 4325.402881665999, "count": 1, "self": 2.902477410000756, "children": { "TrainerController._reset_env": { "total": 4.396745334000229, "count": 10, "self": 4.396745334000229 }, "TrainerController.advance": { "total": 4317.877548278999, "count": 130127, "self": 3.2170668417693378, "children": { "env_step": { "total": 3526.761476744141, "count": 130127, "self": 2715.4749513111624, "children": { "SubprocessEnvManager._take_step": { "total": 809.4626237950429, "count": 130127, "self": 21.594525465990955, "children": { "TorchPolicy.evaluate": { "total": 787.8680983290519, "count": 258410, "self": 787.8680983290519 } } }, "workers": { "total": 1.8239016379355917, "count": 130127, "self": 0.0, "children": { "worker_root": { "total": 4314.736687949988, "count": 130127, "is_parallel": true, "self": 2027.5245090459962, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007087034000164749, "count": 2, "is_parallel": true, "self": 0.004612600000086786, "children": { "_process_rank_one_or_two_observation": { "total": 0.002474434000077963, "count": 8, "is_parallel": true, "self": 0.002474434000077963 } } }, "UnityEnvironment.step": { "total": 0.046085245000085706, "count": 1, "is_parallel": true, "self": 0.0014357779999727427, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009839350000220293, "count": 1, "is_parallel": true, "self": 0.0009839350000220293 }, "communicator.exchange": { "total": 0.039702536000049804, "count": 1, "is_parallel": true, "self": 0.039702536000049804 }, "steps_from_proto": { "total": 0.00396299600004113, "count": 2, "is_parallel": true, "self": 0.0007013830000914822, "children": { "_process_rank_one_or_two_observation": { "total": 0.003261612999949648, "count": 8, "is_parallel": true, "self": 0.003261612999949648 } } } } } } }, "UnityEnvironment.step": { "total": 2287.19115509299, "count": 130126, "is_parallel": true, "self": 150.14014961099747, "children": { "UnityEnvironment._generate_step_input": { "total": 96.98945310300167, "count": 130126, "is_parallel": true, "self": 96.98945310300167 }, "communicator.exchange": { "total": 1585.8236871589738, "count": 130126, "is_parallel": true, "self": 1585.8236871589738 }, "steps_from_proto": { "total": 454.23786522001683, "count": 260252, "is_parallel": true, "self": 72.38366873723044, "children": { "_process_rank_one_or_two_observation": { "total": 381.8541964827864, "count": 1041008, "is_parallel": true, "self": 381.8541964827864 } } } } }, "steps_from_proto": { "total": 0.021023811001668946, "count": 18, "is_parallel": true, "self": 0.004344080003875206, "children": { "_process_rank_one_or_two_observation": { "total": 0.01667973099779374, "count": 72, "is_parallel": true, "self": 0.01667973099779374 } } } } } } } } }, "trainer_advance": { "total": 787.899004693089, "count": 130127, "self": 26.770781131061085, "children": { "process_trajectory": { "total": 220.12287244802428, "count": 130127, "self": 219.07793029802428, "children": { "RLTrainer._checkpoint": { "total": 1.0449421499999971, "count": 4, "self": 1.0449421499999971 } } }, "_update_policy": { "total": 541.0053511140036, "count": 92, "self": 321.37470971999164, "children": { "TorchPOCAOptimizer.update": { "total": 219.63064139401195, "count": 2763, "self": 219.63064139401195 } } } } } } }, "trainer_threads": { "total": 9.409995982423425e-07, "count": 1, "self": 9.409995982423425e-07 }, "TrainerController._save_models": { "total": 0.22610970200003067, "count": 1, "self": 0.0021551270001509693, "children": { "RLTrainer._checkpoint": { "total": 0.2239545749998797, "count": 1, "self": 0.2239545749998797 } } } } } } }