{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4766329526901245, "min": 1.4021979570388794, "max": 3.2957522869110107, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27878.830078125, "min": 18786.455078125, "max": 151363.53125, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 63.11538461538461, "min": 42.79824561403509, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19692.0, "min": 12072.0, "max": 29324.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1590.4476711503166, "min": 1186.7538854705454, "max": 1634.7606450267947, "count": 4858 }, "SoccerTwos.Self-play.ELO.sum": { "value": 248109.8366994494, "min": 2379.1506710439553, "max": 353695.8270168188, "count": 4858 }, "SoccerTwos.Step.mean": { "value": 49999984.0, "min": 9682.0, "max": 49999984.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999984.0, "min": 9682.0, "max": 49999984.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.042247042059898376, "min": -0.15632691979408264, "max": 0.19411611557006836, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -6.5482916831970215, "min": -23.311351776123047, "max": 26.790565490722656, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04453893005847931, "min": -0.1584469974040985, "max": 0.19315099716186523, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.903533935546875, "min": -23.5950927734375, "max": 27.63677215576172, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.031687744202152375, "min": -0.7222222222222222, "max": 0.5494382939440139, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.911600351333618, "min": -62.02480012178421, "max": 66.96879971027374, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.031687744202152375, "min": -0.7222222222222222, "max": 0.5494382939440139, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.911600351333618, "min": -62.02480012178421, "max": 66.96879971027374, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019331093134436136, "min": 0.009575133499068519, "max": 0.026104124978883193, "count": 2414 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019331093134436136, "min": 0.009575133499068519, "max": 0.026104124978883193, "count": 2414 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09118815660476684, "min": 1.4396120846527082e-07, "max": 0.11782409995794296, "count": 2414 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09118815660476684, "min": 1.4396120846527082e-07, "max": 0.11782409995794296, "count": 2414 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09180710191528002, "min": 1.5992417085423464e-07, "max": 0.12035028859972954, "count": 2414 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09180710191528002, "min": 1.5992417085423464e-07, "max": 0.12035028859972954, "count": 2414 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2414 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2414 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2414 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2414 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2414 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2414 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681856682", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:39:03) \n[GCC 11.3.0]", "command_line_arguments": "/home/hussam/miniconda3/envs/hf-course/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=../training-envs-executables/linux/SoccerTwos/SoccerTwos --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": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1681930714" }, "total": 74031.646921976, "count": 1, "self": 0.7349243220232893, "children": { "run_training.setup": { "total": 0.014265656998759368, "count": 1, "self": 0.014265656998759368 }, "TrainerController.start_learning": { "total": 74030.89773199699, "count": 1, "self": 58.47657646048174, "children": { "TrainerController._reset_env": { "total": 9.185247391069424, "count": 250, "self": 9.185247391069424 }, "TrainerController.advance": { "total": 73963.03163965343, "count": 3416258, "self": 60.97298695490463, "children": { "env_step": { "total": 53533.00024160396, "count": 3416258, "self": 41902.776559555656, "children": { "SubprocessEnvManager._take_step": { "total": 11593.00698915432, "count": 3416258, "self": 307.7760565175413, "children": { "TorchPolicy.evaluate": { "total": 11285.23093263678, "count": 6299338, "self": 11285.23093263678 } } }, "workers": { "total": 37.21669289398051, "count": 3416258, "self": 0.0, "children": { "worker_root": { "total": 73957.01397453842, "count": 3416258, "is_parallel": true, "self": 38488.79879444286, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002217400997324148, "count": 2, "is_parallel": true, "self": 0.0008064649955485947, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014109360017755534, "count": 8, "is_parallel": true, "self": 0.0014109360017755534 } } }, "UnityEnvironment.step": { "total": 0.021436210998217575, "count": 1, "is_parallel": true, "self": 0.00040283200360136107, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033020899718394503, "count": 1, "is_parallel": true, "self": 0.00033020899718394503 }, "communicator.exchange": { "total": 0.019391777997952886, "count": 1, "is_parallel": true, "self": 0.019391777997952886 }, "steps_from_proto": { "total": 0.0013113919994793832, "count": 2, "is_parallel": true, "self": 0.0002726010061451234, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010387909933342598, "count": 8, "is_parallel": true, "self": 0.0010387909933342598 } } } } } } }, "UnityEnvironment.step": { "total": 35467.859068687496, "count": 3416257, "is_parallel": true, "self": 1517.1600954529858, "children": { "UnityEnvironment._generate_step_input": { "total": 917.9501856739735, "count": 3416257, "is_parallel": true, "self": 917.9501856739735 }, "communicator.exchange": { "total": 28300.287166050155, "count": 3416257, "is_parallel": true, "self": 28300.287166050155 }, "steps_from_proto": { "total": 4732.461621510378, "count": 6832514, "is_parallel": true, "self": 940.2711248400847, "children": { "_process_rank_one_or_two_observation": { "total": 3792.190496670293, "count": 27330056, "is_parallel": true, "self": 3792.190496670293 } } } } }, "steps_from_proto": { "total": 0.3561114080657717, "count": 498, "is_parallel": true, "self": 0.07101363827678142, "children": { "_process_rank_one_or_two_observation": { "total": 0.28509776978899026, "count": 1992, "is_parallel": true, "self": 0.28509776978899026 } } } } } } } } }, "trainer_advance": { "total": 20369.05841109457, "count": 3416258, "self": 392.42898665456596, "children": { "process_trajectory": { "total": 6636.435676977926, "count": 3416258, "self": 6611.067409481944, "children": { "RLTrainer._checkpoint": { "total": 25.368267495981854, "count": 100, "self": 25.368267495981854 } } }, "_update_policy": { "total": 13340.193747462079, "count": 2414, "self": 5864.559832947329, "children": { "TorchPOCAOptimizer.update": { "total": 7475.63391451475, "count": 72420, "self": 7475.63391451475 } } } } } } }, "trainer_threads": { "total": 5.420006345957518e-07, "count": 1, "self": 5.420006345957518e-07 }, "TrainerController._save_models": { "total": 0.2042679500009399, "count": 1, "self": 0.003651466002338566, "children": { "RLTrainer._checkpoint": { "total": 0.20061648399860132, "count": 1, "self": 0.20061648399860132 } } } } } } }