{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9135105609893799, "min": 1.8966606855392456, "max": 3.295762777328491, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37351.7265625, "min": 28621.5078125, "max": 130955.078125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 51.4375, "min": 39.604838709677416, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19752.0, "min": 10652.0, "max": 30012.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1487.5214108661778, "min": 1191.3766706051888, "max": 1489.7959330171645, "count": 496 }, "SoccerTwos.Self-play.ELO.sum": { "value": 285604.11088630615, "min": 2390.072751685243, "max": 361218.1607592035, "count": 496 }, "SoccerTwos.Step.mean": { "value": 4999964.0, "min": 9022.0, "max": 4999964.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999964.0, "min": 9022.0, "max": 4999964.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.04535470902919769, "min": -0.11993592232465744, "max": 0.19004863500595093, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 8.662749290466309, "min": -23.748119354248047, "max": 27.715343475341797, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.04250567778944969, "min": -0.1142832413315773, "max": 0.19538632035255432, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 8.118584632873535, "min": -23.947742462158203, "max": 27.989952087402344, "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": -0.022307857168906646, "min": -0.6929510211458012, "max": 0.46573613371167866, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.260800719261169, "min": -63.485599994659424, "max": 55.42259991168976, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.022307857168906646, "min": -0.6929510211458012, "max": 0.46573613371167866, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.260800719261169, "min": -63.485599994659424, "max": 55.42259991168976, "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": 0.016151578600207963, "min": 0.011049103082041257, "max": 0.0235756105791855, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016151578600207963, "min": 0.011049103082041257, "max": 0.0235756105791855, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10882534260551134, "min": 0.0009062568754112969, "max": 0.12459699138998985, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10882534260551134, "min": 0.0009062568754112969, "max": 0.12459699138998985, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1109501118461291, "min": 0.0009173607521612818, "max": 0.12684522792696953, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1109501118461291, "min": 0.0009173607521612818, "max": 0.12684522792696953, "count": 240 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677071778", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\emanu\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=poca-SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cu116", "numpy_version": "1.21.2", "end_time_seconds": "1677077594" }, "total": 5815.6003114000005, "count": 1, "self": 0.2012739000010697, "children": { "run_training.setup": { "total": 0.07008039999999993, "count": 1, "self": 0.07008039999999993 }, "TrainerController.start_learning": { "total": 5815.3289571, "count": 1, "self": 4.1021847000583875, "children": { "TrainerController._reset_env": { "total": 3.2602931999977818, "count": 25, "self": 3.2602931999977818 }, "TrainerController.advance": { "total": 5807.8198382999435, "count": 343126, "self": 3.8975711998018596, "children": { "env_step": { "total": 4052.742351500123, "count": 343126, "self": 2462.6775483003303, "children": { "SubprocessEnvManager._take_step": { "total": 1587.5271079999739, "count": 343126, "self": 27.31333789962173, "children": { "TorchPolicy.evaluate": { "total": 1560.2137701003521, "count": 632066, "self": 1560.2137701003521 } } }, "workers": { "total": 2.537695199818991, "count": 343126, "self": 0.0, "children": { "worker_root": { "total": 5807.592962700092, "count": 343126, "is_parallel": true, "self": 3826.715853800153, "children": { "steps_from_proto": { "total": 0.029419499998849297, "count": 50, "is_parallel": true, "self": 0.005730799995375291, "children": { "_process_rank_one_or_two_observation": { "total": 0.023688700003474006, "count": 200, "is_parallel": true, "self": 0.023688700003474006 } } }, "UnityEnvironment.step": { "total": 1980.8476893999402, "count": 343126, "is_parallel": true, "self": 122.36145349993035, "children": { "UnityEnvironment._generate_step_input": { "total": 101.9879514003275, "count": 343126, "is_parallel": true, "self": 101.9879514003275 }, "communicator.exchange": { "total": 1399.4482094999576, "count": 343126, "is_parallel": true, "self": 1399.4482094999576 }, "steps_from_proto": { "total": 357.05007499972476, "count": 686252, "is_parallel": true, "self": 68.74486049933853, "children": { "_process_rank_one_or_two_observation": { "total": 288.3052145003862, "count": 2745008, "is_parallel": true, "self": 288.3052145003862 } } } } } } } } } } }, "trainer_advance": { "total": 1751.1799156000186, "count": 343126, "self": 33.28170960003922, "children": { "process_trajectory": { "total": 728.353284099981, "count": 343126, "self": 727.0889033999805, "children": { "RLTrainer._checkpoint": { "total": 1.2643807000005154, "count": 10, "self": 1.2643807000005154 } } }, "_update_policy": { "total": 989.5449218999983, "count": 240, "self": 552.6703163000046, "children": { "TorchPOCAOptimizer.update": { "total": 436.87460559999363, "count": 7206, "self": 436.87460559999363 } } } } } } }, "trainer_threads": { "total": 6.000000212225132e-07, "count": 1, "self": 6.000000212225132e-07 }, "TrainerController._save_models": { "total": 0.1466402999994898, "count": 1, "self": 0.024768599999333674, "children": { "RLTrainer._checkpoint": { "total": 0.12187170000015612, "count": 1, "self": 0.12187170000015612 } } } } } } }