{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6823278665542603, "min": 1.4995876550674438, "max": 1.7959285974502563, "count": 1501 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32516.033203125, "min": 479.8680419921875, "max": 43333.859375, "count": 1501 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 74.25757575757575, "min": 8.0, "max": 136.64864864864865, "count": 1501 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19604.0, "min": 32.0, "max": 21404.0, "count": 1501 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1147.8665953764862, "min": 1084.5960075216822, "max": 1234.5226613098396, "count": 1501 }, "SoccerTwos.Self-play.ELO.sum": { "value": 151518.39058969618, "min": 2400.0, "max": 200036.12895520366, "count": 1501 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1501 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1501 }, "SoccerTwos.Step.mean": { "value": 49999932.0, "min": 35009978.0, "max": 49999932.0, "count": 1500 }, "SoccerTwos.Step.sum": { "value": 49999932.0, "min": 35009978.0, "max": 49999932.0, "count": 1500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.024236446246504784, "min": -0.16502393782138824, "max": 0.0948086678981781, "count": 1500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.223447322845459, "min": -17.155866622924805, "max": 12.230318069458008, "count": 1500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.022488346323370934, "min": -0.16745972633361816, "max": 0.09007298201322556, "count": 1500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.990950107574463, "min": -17.750730514526367, "max": 11.619414329528809, "count": 1500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.04841503792239311, "min": -0.4856056604745253, "max": 0.39328160190582273, "count": 1500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -6.439200043678284, "min": -58.428800106048584, "max": 49.160200238227844, "count": 1500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.04841503792239311, "min": -0.4856056604745253, "max": 0.39328160190582273, "count": 1500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -6.439200043678284, "min": -58.428800106048584, "max": 49.160200238227844, "count": 1500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.04268376357657345, "min": 0.03569160518644933, "max": 0.04893063144398886, "count": 726 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.04268376357657345, "min": 0.03569160518644933, "max": 0.04893063144398886, "count": 726 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.06262996106555588, "min": 0.0473321278889974, "max": 0.07791101605745784, "count": 726 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.06262996106555588, "min": 0.0473321278889974, "max": 0.07791101605745784, "count": 726 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.06422486947032444, "min": 0.04848482825776987, "max": 0.08058265910336845, "count": 726 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.06422486947032444, "min": 0.04848482825776987, "max": 0.08058265910336845, "count": 726 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00030000000000000003, "min": 0.00030000000000000003, "max": 0.0003000000000000001, "count": 726 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00030000000000000003, "min": 0.00030000000000000003, "max": 0.0003000000000000001, "count": 726 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.19999999999999998, "min": 0.19999999999999993, "max": 0.19999999999999998, "count": 726 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.19999999999999998, "min": 0.19999999999999993, "max": 0.19999999999999998, "count": 726 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 726 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 726 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690418677", "python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]", "command_line_arguments": "/home/alexis/anaconda3/envs/versus/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos0 --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1690470205" }, "total": 51527.679611329004, "count": 1, "self": 0.6461794790084241, "children": { "run_training.setup": { "total": 0.023073071999988315, "count": 1, "self": 0.023073071999988315 }, "TrainerController.start_learning": { "total": 51527.010358777996, "count": 1, "self": 37.231464410651824, "children": { "TrainerController._reset_env": { "total": 11.872461443997508, "count": 76, "self": 11.872461443997508 }, "TrainerController.advance": { "total": 51477.28743136634, "count": 1011465, "self": 35.89632126504148, "children": { "env_step": { "total": 38753.07606577534, "count": 1011465, "self": 30744.57442039963, "children": { "SubprocessEnvManager._take_step": { "total": 7984.230752578262, "count": 1011465, "self": 220.57855452041804, "children": { "TorchPolicy.evaluate": { "total": 7763.652198057844, "count": 1885450, "self": 7763.652198057844 } } }, "workers": { "total": 24.270892797450415, "count": 1011465, "self": 0.0, "children": { "worker_root": { "total": 51452.27876813507, "count": 1011465, "is_parallel": true, "self": 25991.474076333314, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005347751000272183, "count": 2, "is_parallel": true, "self": 0.0018378200004462997, "children": { "_process_rank_one_or_two_observation": { "total": 0.003509930999825883, "count": 8, "is_parallel": true, "self": 0.003509930999825883 } } }, "UnityEnvironment.step": { "total": 0.04815375799989852, "count": 1, "is_parallel": true, "self": 0.0016551839999010554, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0019433340000887256, "count": 1, "is_parallel": true, "self": 0.0019433340000887256 }, "communicator.exchange": { "total": 0.04011248400001932, "count": 1, "is_parallel": true, "self": 0.04011248400001932 }, "steps_from_proto": { "total": 0.004442755999889414, "count": 2, "is_parallel": true, "self": 0.0008932469997944281, "children": { "_process_rank_one_or_two_observation": { "total": 0.003549509000094986, "count": 8, "is_parallel": true, "self": 0.003549509000094986 } } } } } } }, "steps_from_proto": { "total": 0.30144138906121043, "count": 150, "is_parallel": true, "self": 0.059094461090353434, "children": { "_process_rank_one_or_two_observation": { "total": 0.242346927970857, "count": 600, "is_parallel": true, "self": 0.242346927970857 } } }, "UnityEnvironment.step": { "total": 25460.503250412694, "count": 1011464, "is_parallel": true, "self": 1223.8319172887786, "children": { "UnityEnvironment._generate_step_input": { "total": 1342.7371242024376, "count": 1011464, "is_parallel": true, "self": 1342.7371242024376 }, "communicator.exchange": { "total": 19162.25508771095, "count": 1011464, "is_parallel": true, "self": 19162.25508771095 }, "steps_from_proto": { "total": 3731.6791212105254, "count": 2022928, "is_parallel": true, "self": 748.2843993071174, "children": { "_process_rank_one_or_two_observation": { "total": 2983.394721903408, "count": 8091712, "is_parallel": true, "self": 2983.394721903408 } } } } } } } } } } }, "trainer_advance": { "total": 12688.315044325958, "count": 1011465, "self": 239.42839476415065, "children": { "process_trajectory": { "total": 4136.992882396729, "count": 1011465, "self": 4116.678543270726, "children": { "RLTrainer._checkpoint": { "total": 20.31433912600346, "count": 31, "self": 20.31433912600346 } } }, "_update_policy": { "total": 8311.893767165078, "count": 726, "self": 4894.886106728573, "children": { "TorchPOCAOptimizer.update": { "total": 3417.007660436505, "count": 41496, "self": 3417.007660436505 } } } } } } }, "trainer_threads": { "total": 1.7400016076862812e-06, "count": 1, "self": 1.7400016076862812e-06 }, "TrainerController._save_models": { "total": 0.6189998170011677, "count": 1, "self": 0.006280888002947904, "children": { "RLTrainer._checkpoint": { "total": 0.6127189289982198, "count": 1, "self": 0.6127189289982198 } } } } } } }