{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3674710988998413, "min": 1.2743571996688843, "max": 3.2957520484924316, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 26911.830078125, "min": 7467.720703125, "max": 146179.828125, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.48863636363637, "min": 38.503937007874015, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19180.0, "min": 8444.0, "max": 31572.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1609.0549223551425, "min": 1193.5637314241378, "max": 1687.1228004941863, "count": 4983 }, "SoccerTwos.Self-play.ELO.sum": { "value": 283193.6663345051, "min": 2390.2667953790874, "max": 395012.950937358, "count": 4983 }, "SoccerTwos.Step.mean": { "value": 49999984.0, "min": 9700.0, "max": 49999984.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999984.0, "min": 9700.0, "max": 49999984.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.01791178621351719, "min": -0.15846297144889832, "max": 0.18217571079730988, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 3.1524744033813477, "min": -29.18328857421875, "max": 27.278125762939453, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.019399767741560936, "min": -0.15720243752002716, "max": 0.18851645290851593, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 3.4143590927124023, "min": -29.116409301757812, "max": 26.90338897705078, "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": 0.04263863848014311, "min": -0.7058823529411765, "max": 0.5392952362696329, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 7.504400372505188, "min": -69.86080002784729, "max": 59.427199721336365, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.04263863848014311, "min": -0.7058823529411765, "max": 0.5392952362696329, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 7.504400372505188, "min": -69.86080002784729, "max": 59.427199721336365, "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": 0.01591464158069963, "min": 0.009518874058267101, "max": 0.027558063979571064, "count": 2425 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01591464158069963, "min": 0.009518874058267101, "max": 0.027558063979571064, "count": 2425 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11939294412732124, "min": 0.0001308333618605199, "max": 0.13057637959718704, "count": 2425 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11939294412732124, "min": 0.0001308333618605199, "max": 0.13057637959718704, "count": 2425 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.12059490208824476, "min": 0.00013482455760822633, "max": 0.1327956276635329, "count": 2425 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.12059490208824476, "min": 0.00013482455760822633, "max": 0.1327956276635329, "count": 2425 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2425 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2425 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2425 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2425 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2425 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2425 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675379277", "python_version": "3.9.16 (main, Jan 11 2023, 16:05:54) \n[GCC 11.2.0]", "command_line_arguments": "/home/ubuntu/anaconda3/envs/hf-marl-py39/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=baseline --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+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1675464934" }, "total": 85656.847560273, "count": 1, "self": 0.21941732898994815, "children": { "run_training.setup": { "total": 0.008694373999787786, "count": 1, "self": 0.008694373999787786 }, "TrainerController.start_learning": { "total": 85656.61944857001, "count": 1, "self": 50.142873163262266, "children": { "TrainerController._reset_env": { "total": 4.205210946020998, "count": 250, "self": 4.205210946020998 }, "TrainerController.advance": { "total": 85602.13795859471, "count": 3464821, "self": 50.714252502206364, "children": { "env_step": { "total": 41958.58532290886, "count": 3464821, "self": 34877.88786644537, "children": { "SubprocessEnvManager._take_step": { "total": 7051.346318683453, "count": 3464821, "self": 318.7034182219968, "children": { "TorchPolicy.evaluate": { "total": 6732.6429004614565, "count": 6277744, "self": 6732.6429004614565 } } }, "workers": { "total": 29.35113778003233, "count": 3464821, "self": 0.0, "children": { "worker_root": { "total": 85567.51348396574, "count": 3464821, "is_parallel": true, "self": 56373.08279523491, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019538819997251267, "count": 2, "is_parallel": true, "self": 0.00047013599942147266, "children": { "_process_rank_one_or_two_observation": { "total": 0.001483746000303654, "count": 8, "is_parallel": true, "self": 0.001483746000303654 } } }, "UnityEnvironment.step": { "total": 0.021857695000107924, "count": 1, "is_parallel": true, "self": 0.00048443000105180545, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003383149996807333, "count": 1, "is_parallel": true, "self": 0.0003383149996807333 }, "communicator.exchange": { "total": 0.01970380100010516, "count": 1, "is_parallel": true, "self": 0.01970380100010516 }, "steps_from_proto": { "total": 0.0013311489992702263, "count": 2, "is_parallel": true, "self": 0.00027363400022295536, "children": { "_process_rank_one_or_two_observation": { "total": 0.001057514999047271, "count": 8, "is_parallel": true, "self": 0.001057514999047271 } } } } } } }, "UnityEnvironment.step": { "total": 29194.103772531784, "count": 3464820, "is_parallel": true, "self": 1504.5875829327051, "children": { "UnityEnvironment._generate_step_input": { "total": 953.5364729113753, "count": 3464820, "is_parallel": true, "self": 953.5364729113753 }, "communicator.exchange": { "total": 22744.648049008854, "count": 3464820, "is_parallel": true, "self": 22744.648049008854 }, "steps_from_proto": { "total": 3991.33166767885, "count": 6929640, "is_parallel": true, "self": 778.0837197021174, "children": { "_process_rank_one_or_two_observation": { "total": 3213.2479479767326, "count": 27718560, "is_parallel": true, "self": 3213.2479479767326 } } } } }, "steps_from_proto": { "total": 0.32691619904562685, "count": 498, "is_parallel": true, "self": 0.06449715336293593, "children": { "_process_rank_one_or_two_observation": { "total": 0.2624190456826909, "count": 1992, "is_parallel": true, "self": 0.2624190456826909 } } } } } } } } }, "trainer_advance": { "total": 43592.83838318365, "count": 3464821, "self": 366.1398350126765, "children": { "process_trajectory": { "total": 7247.233189150913, "count": 3464821, "self": 7233.505255685897, "children": { "RLTrainer._checkpoint": { "total": 13.727933465015667, "count": 100, "self": 13.727933465015667 } } }, "_update_policy": { "total": 35979.46535902006, "count": 2425, "self": 6382.33976575268, "children": { "TorchPOCAOptimizer.update": { "total": 29597.12559326738, "count": 72756, "self": 29597.12559326738 } } } } } } }, "trainer_threads": { "total": 6.780028343200684e-07, "count": 1, "self": 6.780028343200684e-07 }, "TrainerController._save_models": { "total": 0.13340518801123835, "count": 1, "self": 0.0011369240091880783, "children": { "RLTrainer._checkpoint": { "total": 0.13226826400205027, "count": 1, "self": 0.13226826400205027 } } } } } } }