{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.018131732940674, "min": 2.0079426765441895, "max": 3.295750379562378, "count": 527 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40491.79296875, "min": 26633.43359375, "max": 119030.203125, "count": 527 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 52.75268817204301, "min": 45.58715596330275, "max": 999.0, "count": 527 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19624.0, "min": 12888.0, "max": 29152.0, "count": 527 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1561.658800339032, "min": 1194.7717755684432, "max": 1561.658800339032, "count": 501 }, "SoccerTwos.Self-play.ELO.sum": { "value": 290468.53686305997, "min": 2390.07623619915, "max": 323100.7924516831, "count": 501 }, "SoccerTwos.Step.mean": { "value": 5269927.0, "min": 9592.0, "max": 5269927.0, "count": 527 }, "SoccerTwos.Step.sum": { "value": 5269927.0, "min": 9592.0, "max": 5269927.0, "count": 527 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.10578177869319916, "min": -0.08186466991901398, "max": 0.15567800402641296, "count": 527 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 19.781192779541016, "min": -13.56808090209961, "max": 22.57331085205078, "count": 527 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.11103010177612305, "min": -0.08205690234899521, "max": 0.16004608571529388, "count": 527 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 20.76262855529785, "min": -14.819267272949219, "max": 23.206682205200195, "count": 527 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 527 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 527 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.12642994602733754, "min": -0.6666666666666666, "max": 0.586328884628084, "count": 527 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 23.64239990711212, "min": -44.62840008735657, "max": 63.831600069999695, "count": 527 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.12642994602733754, "min": -0.6666666666666666, "max": 0.586328884628084, "count": 527 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 23.64239990711212, "min": -44.62840008735657, "max": 63.831600069999695, "count": 527 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 527 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 527 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01357572532724589, "min": 0.009770415224678194, "max": 0.02506676627866303, "count": 250 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01357572532724589, "min": 0.009770415224678194, "max": 0.02506676627866303, "count": 250 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10331122626860936, "min": 1.678222944671385e-06, "max": 0.11448846409718196, "count": 250 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10331122626860936, "min": 1.678222944671385e-06, "max": 0.11448846409718196, "count": 250 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1049035037557284, "min": 1.7105347675775799e-06, "max": 0.11663524731993676, "count": 250 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1049035037557284, "min": 1.7105347675775799e-06, "max": 0.11663524731993676, "count": 250 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 250 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 250 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 250 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 250 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 250 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 250 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713557346", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\HP\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos10 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1713611332" }, "total": 53992.8446653001, "count": 1, "self": 1.0598451001569629, "children": { "run_training.setup": { "total": 0.15680680004879832, "count": 1, "self": 0.15680680004879832 }, "TrainerController.start_learning": { "total": 53991.628013399895, "count": 1, "self": 14.891631632577628, "children": { "TrainerController._reset_env": { "total": 10.832164999912493, "count": 27, "self": 10.832164999912493 }, "TrainerController.advance": { "total": 53965.6238859673, "count": 352674, "self": 15.647533042822033, "children": { "env_step": { "total": 13393.392757215188, "count": 352674, "self": 10351.006479708827, "children": { "SubprocessEnvManager._take_step": { "total": 3032.6104095219634, "count": 352674, "self": 99.78621430543717, "children": { "TorchPolicy.evaluate": { "total": 2932.8241952165263, "count": 669908, "self": 2932.8241952165263 } } }, "workers": { "total": 9.775867984397337, "count": 352674, "self": 0.0, "children": { "worker_root": { "total": 53959.25035351992, "count": 352674, "is_parallel": true, "self": 45638.409207116114, "children": { "steps_from_proto": { "total": 0.1062490998301655, "count": 54, "is_parallel": true, "self": 0.022141199908219278, "children": { "_process_rank_one_or_two_observation": { "total": 0.08410789992194623, "count": 216, "is_parallel": true, "self": 0.08410789992194623 } } }, "UnityEnvironment.step": { "total": 8320.734897303977, "count": 352674, "is_parallel": true, "self": 479.3871183008887, "children": { "UnityEnvironment._generate_step_input": { "total": 480.52795000211336, "count": 352674, "is_parallel": true, "self": 480.52795000211336 }, "communicator.exchange": { "total": 5772.485165696009, "count": 352674, "is_parallel": true, "self": 5772.485165696009 }, "steps_from_proto": { "total": 1588.334663304966, "count": 705348, "is_parallel": true, "self": 311.8247044926975, "children": { "_process_rank_one_or_two_observation": { "total": 1276.5099588122685, "count": 2821392, "is_parallel": true, "self": 1276.5099588122685 } } } } } } } } } } }, "trainer_advance": { "total": 40556.58359570929, "count": 352674, "self": 97.23468627466355, "children": { "process_trajectory": { "total": 20662.991330934456, "count": 352674, "self": 20660.318571434473, "children": { "RLTrainer._checkpoint": { "total": 2.6727594999829307, "count": 10, "self": 2.6727594999829307 } } }, "_update_policy": { "total": 19796.357578500174, "count": 251, "self": 1426.3043278991245, "children": { "TorchPOCAOptimizer.update": { "total": 18370.05325060105, "count": 7504, "self": 18370.05325060105 } } } } } } }, "trainer_threads": { "total": 3.200024366378784e-06, "count": 1, "self": 3.200024366378784e-06 }, "TrainerController._save_models": { "total": 0.28032760007772595, "count": 1, "self": 0.004670300055295229, "children": { "RLTrainer._checkpoint": { "total": 0.2756573000224307, "count": 1, "self": 0.2756573000224307 } } } } } } }