{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1816980838775635, "min": 3.116131067276001, "max": 3.295670509338379, "count": 100 }, "SoccerTwos.Policy.Entropy.sum": { "value": 47954.5546875, "min": 27688.8515625, "max": 114850.75, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 829.4, "min": 454.1666666666667, "max": 999.0, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 16588.0, "min": 15168.0, "max": 22992.0, "count": 100 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1210.365539993249, "min": 1199.3635640870189, "max": 1211.6703251820352, "count": 78 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2420.731079986498, "min": 2401.494438687959, "max": 14435.733189035422, "count": 78 }, "SoccerTwos.Step.mean": { "value": 999164.0, "min": 9368.0, "max": 999164.0, "count": 100 }, "SoccerTwos.Step.sum": { "value": 999164.0, "min": 9368.0, "max": 999164.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.003331040032207966, "min": -0.01840142533183098, "max": 0.02944786474108696, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.0366414412856102, "min": -0.28103792667388916, "max": 0.3411446213722229, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0033731332514435053, "min": -0.020900800824165344, "max": 0.029286708682775497, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.03710446506738663, "min": -0.27047470211982727, "max": 0.34248441457748413, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.15414545752785422, "min": -0.5, "max": 0.29737143431391033, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 1.6956000328063965, "min": -8.0, "max": 4.163200080394745, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.15414545752785422, "min": -0.5, "max": 0.29737143431391033, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 1.6956000328063965, "min": -8.0, "max": 4.163200080394745, "count": 100 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018614301865454763, "min": 0.014748547625398107, "max": 0.02044941791148934, "count": 46 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018614301865454763, "min": 0.014748547625398107, "max": 0.02044941791148934, "count": 46 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 8.391827074471318e-05, "min": 2.8596786008468675e-05, "max": 0.005075956632693609, "count": 46 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 8.391827074471318e-05, "min": 2.8596786008468675e-05, "max": 0.005075956632693609, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 8.312994226192435e-05, "min": 3.061445925898927e-05, "max": 0.004852803330868483, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 8.312994226192435e-05, "min": 3.061445925898927e-05, "max": 0.004852803330868483, "count": 46 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 46 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 46 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 46 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 46 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694778187", "python_version": "3.9.18 (main, Sep 11 2023, 14:09:26) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\Admin\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1694789148" }, "total": 10961.7643531, "count": 1, "self": 1.1519243999991886, "children": { "run_training.setup": { "total": 0.1234504000000003, "count": 1, "self": 0.1234504000000003 }, "TrainerController.start_learning": { "total": 10960.4889783, "count": 1, "self": 1.8804855998751009, "children": { "TrainerController._reset_env": { "total": 5.867669500000613, "count": 5, "self": 5.867669500000613 }, "TrainerController.advance": { "total": 10952.548825900125, "count": 65368, "self": 2.1049440004971984, "children": { "env_step": { "total": 1774.8235136998833, "count": 65368, "self": 1421.8256293999157, "children": { "SubprocessEnvManager._take_step": { "total": 351.6677326002043, "count": 65368, "self": 12.72254080019951, "children": { "TorchPolicy.evaluate": { "total": 338.9451918000048, "count": 129784, "self": 338.9451918000048 } } }, "workers": { "total": 1.3301516997632294, "count": 65368, "self": 0.0, "children": { "worker_root": { "total": 10950.345286499816, "count": 65368, "is_parallel": true, "self": 9783.36622350001, "children": { "steps_from_proto": { "total": 0.014029000001248626, "count": 10, "is_parallel": true, "self": 0.0025410000066559135, "children": { "_process_rank_one_or_two_observation": { "total": 0.011487999994592712, "count": 40, "is_parallel": true, "self": 0.011487999994592712 } } }, "UnityEnvironment.step": { "total": 1166.9650339998047, "count": 65368, "is_parallel": true, "self": 63.75334599966868, "children": { "UnityEnvironment._generate_step_input": { "total": 57.50357560029934, "count": 65368, "is_parallel": true, "self": 57.50357560029934 }, "communicator.exchange": { "total": 836.9641780000907, "count": 65368, "is_parallel": true, "self": 836.9641780000907 }, "steps_from_proto": { "total": 208.74393439974602, "count": 130736, "is_parallel": true, "self": 39.52245620037337, "children": { "_process_rank_one_or_two_observation": { "total": 169.22147819937265, "count": 522944, "is_parallel": true, "self": 169.22147819937265 } } } } } } } } } } }, "trainer_advance": { "total": 9175.620368199745, "count": 65368, "self": 13.980612899562402, "children": { "process_trajectory": { "total": 6750.029844000183, "count": 65368, "self": 6749.2027081001825, "children": { "RLTrainer._checkpoint": { "total": 0.8271359000009397, "count": 2, "self": 0.8271359000009397 } } }, "_update_policy": { "total": 2411.609911299999, "count": 46, "self": 189.76634349997903, "children": { "TorchPOCAOptimizer.update": { "total": 2221.84356780002, "count": 1380, "self": 2221.84356780002 } } } } } } }, "trainer_threads": { "total": 2.999999196617864e-06, "count": 1, "self": 2.999999196617864e-06 }, "TrainerController._save_models": { "total": 0.19199429999935091, "count": 1, "self": 0.01572899999882793, "children": { "RLTrainer._checkpoint": { "total": 0.17626530000052298, "count": 1, "self": 0.17626530000052298 } } } } } } }