{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3785388469696045, "min": 1.2652868032455444, "max": 1.4391518831253052, "count": 100 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27173.7578125, "min": 22449.69921875, "max": 30135.53515625, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 63.58227848101266, "min": 46.15238095238095, "max": 82.76666666666667, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20092.0, "min": 18576.0, "max": 20488.0, "count": 100 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1178.7208169320484, "min": 1178.555471367562, "max": 1210.2889338157947, "count": 100 }, "SoccerTwos.Self-play.ELO.sum": { "value": 186237.88907526364, "min": 142084.47714409293, "max": 252912.33561713746, "count": 100 }, "SoccerTwos.Step.mean": { "value": 999882.0, "min": 9992.0, "max": 999882.0, "count": 100 }, "SoccerTwos.Step.sum": { "value": 999882.0, "min": 9992.0, "max": 999882.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03008103556931019, "min": -0.0897950753569603, "max": 0.029128646478056908, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.72272253036499, "min": -14.01373291015625, "max": 5.2140278816223145, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02984745241701603, "min": -0.0896281972527504, "max": 0.028643064200878143, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.686049938201904, "min": -13.959389686584473, "max": 5.127108573913574, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.044163056999255136, "min": -0.27418914737627487, "max": 0.19249385495425603, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -6.933599948883057, "min": -39.29500025510788, "max": 34.45640003681183, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.044163056999255136, "min": -0.27418914737627487, "max": 0.19249385495425603, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -6.933599948883057, "min": -39.29500025510788, "max": 34.45640003681183, "count": 100 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.0182365807677949, "min": 0.010929412101298415, "max": 0.022865173884201794, "count": 48 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0182365807677949, "min": 0.010929412101298415, "max": 0.022865173884201794, "count": 48 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11022970726092657, "min": 0.09646974230806032, "max": 0.11893880342443784, "count": 48 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11022970726092657, "min": 0.09646974230806032, "max": 0.11893880342443784, "count": 48 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11040919795632362, "min": 0.09642634515961011, "max": 0.1193186196188132, "count": 48 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11040919795632362, "min": 0.09642634515961011, "max": 0.1193186196188132, "count": 48 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 3.5604988131999975e-06, "min": 3.5604988131999975e-06, "max": 0.00029382000206, "count": 48 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 3.5604988131999975e-06, "min": 3.5604988131999975e-06, "max": 0.00029382000206, "count": 48 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10118679999999997, "min": 0.10118679999999997, "max": 0.19794, "count": 48 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.10118679999999997, "min": 0.10118679999999997, "max": 0.19794, "count": 48 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.00012856131999999985, "min": 0.00012856131999999985, "max": 0.009794206000000005, "count": 48 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.00012856131999999985, "min": 0.00012856131999999985, "max": 0.009794206000000005, "count": 48 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680444407", "python_version": "3.8.16 (default, Jan 17 2023, 22:25:28) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Kaush\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn .\\config\\poca\\SoccerTwosPreTrained.yaml --env=.\\training-envs-executables\\SoccerTwos\\SoccerTwos.exe --run-id=poca-SoccerTwos-pretrained150 --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+cu117", "numpy_version": "1.21.2", "end_time_seconds": "1680448456" }, "total": 4048.408677, "count": 1, "self": 0.9526921999995466, "children": { "run_training.setup": { "total": 0.1814833999999994, "count": 1, "self": 0.1814833999999994 }, "TrainerController.start_learning": { "total": 4047.2745014, "count": 1, "self": 3.2528624999790736, "children": { "TrainerController._reset_env": { "total": 9.605797899999864, "count": 5, "self": 9.605797899999864 }, "TrainerController.advance": { "total": 4034.1841748000215, "count": 69292, "self": 3.690406400007305, "children": { "env_step": { "total": 2870.1142315000125, "count": 69292, "self": 1631.9468360999701, "children": { "SubprocessEnvManager._take_step": { "total": 1236.165864500007, "count": 69292, "self": 25.098418099946684, "children": { "TorchPolicy.evaluate": { "total": 1211.0674464000604, "count": 125486, "self": 1211.0674464000604 } } }, "workers": { "total": 2.001530900035384, "count": 69292, "self": 0.0, "children": { "worker_root": { "total": 4036.835178999987, "count": 69292, "is_parallel": true, "self": 2757.2931432999617, "children": { "steps_from_proto": { "total": 0.022451600000070293, "count": 10, "is_parallel": true, "self": 0.004252700000368925, "children": { "_process_rank_one_or_two_observation": { "total": 0.018198899999701368, "count": 40, "is_parallel": true, "self": 0.018198899999701368 } } }, "UnityEnvironment.step": { "total": 1279.5195841000252, "count": 69292, "is_parallel": true, "self": 66.1312259999836, "children": { "UnityEnvironment._generate_step_input": { "total": 51.90662950004355, "count": 69292, "is_parallel": true, "self": 51.90662950004355 }, "communicator.exchange": { "total": 957.0205951999809, "count": 69292, "is_parallel": true, "self": 957.0205951999809 }, "steps_from_proto": { "total": 204.4611334000172, "count": 138584, "is_parallel": true, "self": 45.09512389998633, "children": { "_process_rank_one_or_two_observation": { "total": 159.36600950003086, "count": 554336, "is_parallel": true, "self": 159.36600950003086 } } } } } } } } } } }, "trainer_advance": { "total": 1160.379536900002, "count": 69292, "self": 19.789121699997622, "children": { "process_trajectory": { "total": 599.135403300004, "count": 69292, "self": 598.296133800004, "children": { "RLTrainer._checkpoint": { "total": 0.8392695000000003, "count": 2, "self": 0.8392695000000003 } } }, "_update_policy": { "total": 541.4550119000005, "count": 48, "self": 332.068107299994, "children": { "TorchPOCAOptimizer.update": { "total": 209.38690460000652, "count": 1440, "self": 209.38690460000652 } } } } } } }, "trainer_threads": { "total": 1.0999997357430402e-06, "count": 1, "self": 1.0999997357430402e-06 }, "TrainerController._save_models": { "total": 0.2316651000001002, "count": 1, "self": 0.004850700000133656, "children": { "RLTrainer._checkpoint": { "total": 0.22681439999996655, "count": 1, "self": 0.22681439999996655 } } } } } } }