{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8472766876220703, "min": 1.8125964403152466, "max": 3.2957024574279785, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36709.08203125, "min": 19024.939453125, "max": 105462.4765625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 67.08108108108108, "min": 41.99145299145299, "max": 955.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19856.0, "min": 3728.0, "max": 29388.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1578.1082421814567, "min": 1199.0014391117093, "max": 1621.51053721304, "count": 500 }, "SoccerTwos.Self-play.ELO.sum": { "value": 233560.0198428556, "min": 2398.0028782234185, "max": 371584.588301979, "count": 500 }, "SoccerTwos.Step.mean": { "value": 4999964.0, "min": 9710.0, "max": 4999964.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999964.0, "min": 9710.0, "max": 4999964.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03346812352538109, "min": -0.10147440433502197, "max": 0.18483717739582062, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.953282356262207, "min": -20.19340705871582, "max": 25.692367553710938, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.037251055240631104, "min": -0.10180693119764328, "max": 0.18707722425460815, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.513155937194824, "min": -20.259578704833984, "max": 26.003734588623047, "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": -0.21308378190607638, "min": -0.5, "max": 0.4011777780122227, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -31.536399722099304, "min": -45.79879975318909, "max": 61.599599957466125, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.21308378190607638, "min": -0.5, "max": 0.4011777780122227, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -31.536399722099304, "min": -45.79879975318909, "max": 61.599599957466125, "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": 0.017255713748939645, "min": 0.011526322570474198, "max": 0.02349549486146619, "count": 241 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017255713748939645, "min": 0.011526322570474198, "max": 0.02349549486146619, "count": 241 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09383611952265104, "min": 0.0006294909268035554, "max": 0.12253104994694392, "count": 241 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09383611952265104, "min": 0.0006294909268035554, "max": 0.12253104994694392, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09437257324655851, "min": 0.000640032676650056, "max": 0.12375060990452766, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09437257324655851, "min": 0.000640032676650056, "max": 0.12375060990452766, "count": 241 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 241 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 241 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675455279", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos --run-id=SoccerTwos1 --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1675465546" }, "total": 10266.897011236, "count": 1, "self": 0.38967903400043724, "children": { "run_training.setup": { "total": 0.09854491800001597, "count": 1, "self": 0.09854491800001597 }, "TrainerController.start_learning": { "total": 10266.408787284, "count": 1, "self": 6.86918512520424, "children": { "TrainerController._reset_env": { "total": 6.544008632001805, "count": 25, "self": 6.544008632001805 }, "TrainerController.advance": { "total": 10252.735253358795, "count": 342937, "self": 7.650966929882998, "children": { "env_step": { "total": 7698.2844725632685, "count": 342937, "self": 6009.374341474902, "children": { "SubprocessEnvManager._take_step": { "total": 1684.922113751939, "count": 342937, "self": 48.45838916502498, "children": { "TorchPolicy.evaluate": { "total": 1636.463724586914, "count": 629196, "self": 321.2006332662877, "children": { "TorchPolicy.sample_actions": { "total": 1315.2630913206262, "count": 629196, "self": 1315.2630913206262 } } } } }, "workers": { "total": 3.9880173364276743, "count": 342937, "self": 0.0, "children": { "worker_root": { "total": 10246.81622835373, "count": 342937, "is_parallel": true, "self": 5138.324095843226, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028940809997948236, "count": 2, "is_parallel": true, "self": 0.0008200769993891299, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020740040004056937, "count": 8, "is_parallel": true, "self": 0.0020740040004056937 } } }, "UnityEnvironment.step": { "total": 0.08233596399986709, "count": 1, "is_parallel": true, "self": 0.003028599999652215, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006843710000339343, "count": 1, "is_parallel": true, "self": 0.0006843710000339343 }, "communicator.exchange": { "total": 0.07060301000001346, "count": 1, "is_parallel": true, "self": 0.07060301000001346 }, "steps_from_proto": { "total": 0.008019983000167485, "count": 2, "is_parallel": true, "self": 0.005617966000045271, "children": { "_process_rank_one_or_two_observation": { "total": 0.002402017000122214, "count": 8, "is_parallel": true, "self": 0.002402017000122214 } } } } } } }, "UnityEnvironment.step": { "total": 5108.443098561501, "count": 342936, "is_parallel": true, "self": 285.5037480975352, "children": { "UnityEnvironment._generate_step_input": { "total": 202.70484117832802, "count": 342936, "is_parallel": true, "self": 202.70484117832802 }, "communicator.exchange": { "total": 3658.152320977799, "count": 342936, "is_parallel": true, "self": 3658.152320977799 }, "steps_from_proto": { "total": 962.0821883078388, "count": 685872, "is_parallel": true, "self": 195.61923662575896, "children": { "_process_rank_one_or_two_observation": { "total": 766.4629516820798, "count": 2743488, "is_parallel": true, "self": 766.4629516820798 } } } } }, "steps_from_proto": { "total": 0.04903394900247804, "count": 48, "is_parallel": true, "self": 0.010349801998245312, "children": { "_process_rank_one_or_two_observation": { "total": 0.03868414700423273, "count": 192, "is_parallel": true, "self": 0.03868414700423273 } } } } } } } } }, "trainer_advance": { "total": 2546.799813865643, "count": 342937, "self": 47.23491536578058, "children": { "process_trajectory": { "total": 1121.255497017871, "count": 342937, "self": 1118.9879654338727, "children": { "RLTrainer._checkpoint": { "total": 2.267531583998334, "count": 10, "self": 2.267531583998334 } } }, "_update_policy": { "total": 1378.3094014819917, "count": 241, "self": 846.4225084789098, "children": { "TorchPOCAOptimizer.update": { "total": 531.8868930030819, "count": 7239, "self": 531.8868930030819 } } } } } } }, "trainer_threads": { "total": 1.2389991752570495e-06, "count": 1, "self": 1.2389991752570495e-06 }, "TrainerController._save_models": { "total": 0.2603389289997722, "count": 1, "self": 0.0017856539998319931, "children": { "RLTrainer._checkpoint": { "total": 0.2585532749999402, "count": 1, "self": 0.2585532749999402 } } } } } } }