{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 0.7791455388069153, "min": 0.7624937295913696, "max": 3.295722723007202, "count": 3226 }, "SoccerTwos.Policy.Entropy.sum": { "value": 14884.796875, "min": 14200.68359375, "max": 146859.28125, "count": 3226 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 45.86538461538461, "min": 39.292682926829265, "max": 999.0, "count": 3226 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19080.0, "min": 11136.0, "max": 29296.0, "count": 3226 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1624.6993163392315, "min": 1195.5682471929065, "max": 1675.4064958149786, "count": 3225 }, "SoccerTwos.Self-play.ELO.sum": { "value": 337937.45779856015, "min": 2396.0280775710307, "max": 400193.93976528017, "count": 3225 }, "SoccerTwos.Step.mean": { "value": 32259981.0, "min": 9664.0, "max": 32259981.0, "count": 3226 }, "SoccerTwos.Step.sum": { "value": 32259981.0, "min": 9664.0, "max": 32259981.0, "count": 3226 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03840962424874306, "min": -0.13809826970100403, "max": 0.1878994256258011, "count": 3226 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -8.02761173248291, "min": -29.305511474609375, "max": 25.478267669677734, "count": 3226 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03768490254878998, "min": -0.14155514538288116, "max": 0.18486498296260834, "count": 3226 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -7.876144886016846, "min": -31.07803726196289, "max": 25.072528839111328, "count": 3226 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3226 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3226 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.0010143552670638528, "min": -0.6013857168810708, "max": 0.6171851908719098, "count": 3226 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -0.21200025081634521, "min": -66.77680015563965, "max": 60.29400014877319, "count": 3226 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.0010143552670638528, "min": -0.6013857168810708, "max": 0.6171851908719098, "count": 3226 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -0.21200025081634521, "min": -66.77680015563965, "max": 60.29400014877319, "count": 3226 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3226 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3226 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015469975732654954, "min": 0.009428530762185498, "max": 0.025476174593980733, "count": 1565 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015469975732654954, "min": 0.009428530762185498, "max": 0.025476174593980733, "count": 1565 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11798259566227595, "min": 0.00023185536532158342, "max": 0.1290443571905295, "count": 1565 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11798259566227595, "min": 0.00023185536532158342, "max": 0.1290443571905295, "count": 1565 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.12054882372419039, "min": 0.00023373690686033418, "max": 0.13223507205645244, "count": 1565 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.12054882372419039, "min": 0.00023373690686033418, "max": 0.13223507205645244, "count": 1565 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1565 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1565 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.135493344, "min": 0.135493344, "max": 0.19995901600000007, "count": 1565 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.135493344, "min": 0.135493344, "max": 0.19995901600000007, "count": 1565 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.0017811178656000003, "min": 0.0017811178656000003, "max": 0.0049979548984, "count": 1565 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.0017811178656000003, "min": 0.0017811178656000003, "max": 0.0049979548984, "count": 1565 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677062363", "python_version": "3.8.16 (default, Jan 17 2023, 23:13:24) \n[GCC 11.2.0]", "command_line_arguments": "/home/antoine/anaconda3/envs/hf_drl_unit7/bin/mlagents-learn cfg_base.yaml --env=../SoccerTwos/SoccerTwos.x86_64 --run-id=Base --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1677107818" }, "total": 45454.463184305, "count": 1, "self": 0.18237785199744394, "children": { "run_training.setup": { "total": 0.006511797000712249, "count": 1, "self": 0.006511797000712249 }, "TrainerController.start_learning": { "total": 45454.274294656, "count": 1, "self": 30.29970927356044, "children": { "TrainerController._reset_env": { "total": 4.8319704840114355, "count": 162, "self": 4.8319704840114355 }, "TrainerController.advance": { "total": 45419.005565137435, "count": 2244188, "self": 27.900850920581433, "children": { "env_step": { "total": 34999.42035713118, "count": 2244188, "self": 28603.619322127084, "children": { "SubprocessEnvManager._take_step": { "total": 6377.473117561428, "count": 2244188, "self": 157.06944341419057, "children": { "TorchPolicy.evaluate": { "total": 6220.403674147237, "count": 4051318, "self": 6220.403674147237 } } }, "workers": { "total": 18.327917442669786, "count": 2244187, "self": 0.0, "children": { "worker_root": { "total": 45404.27861819351, "count": 2244187, "is_parallel": true, "self": 20539.20533841079, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025274600002376246, "count": 2, "is_parallel": true, "self": 0.0003966739977840916, "children": { "_process_rank_one_or_two_observation": { "total": 0.002130786002453533, "count": 8, "is_parallel": true, "self": 0.002130786002453533 } } }, "UnityEnvironment.step": { "total": 0.019344760999956634, "count": 1, "is_parallel": true, "self": 0.0009375609988637734, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006344470002659364, "count": 1, "is_parallel": true, "self": 0.0006344470002659364 }, "communicator.exchange": { "total": 0.015185750999989978, "count": 1, "is_parallel": true, "self": 0.015185750999989978 }, "steps_from_proto": { "total": 0.0025870020008369465, "count": 2, "is_parallel": true, "self": 0.00041773600150918355, "children": { "_process_rank_one_or_two_observation": { "total": 0.002169265999327763, "count": 8, "is_parallel": true, "self": 0.002169265999327763 } } } } } } }, "UnityEnvironment.step": { "total": 24864.692314070737, "count": 2244186, "is_parallel": true, "self": 1692.4320398539567, "children": { "UnityEnvironment._generate_step_input": { "total": 1072.3914547570039, "count": 2244186, "is_parallel": true, "self": 1072.3914547570039 }, "communicator.exchange": { "total": 17266.984998667784, "count": 2244186, "is_parallel": true, "self": 17266.984998667784 }, "steps_from_proto": { "total": 4832.883820791993, "count": 4488372, "is_parallel": true, "self": 711.814651623984, "children": { "_process_rank_one_or_two_observation": { "total": 4121.069169168009, "count": 17953488, "is_parallel": true, "self": 4121.069169168009 } } } } }, "steps_from_proto": { "total": 0.38096571198093443, "count": 322, "is_parallel": true, "self": 0.054525434093193326, "children": { "_process_rank_one_or_two_observation": { "total": 0.3264402778877411, "count": 1288, "is_parallel": true, "self": 0.3264402778877411 } } } } } } } } }, "trainer_advance": { "total": 10391.684357085669, "count": 2244187, "self": 213.58864884816103, "children": { "process_trajectory": { "total": 4261.204047678503, "count": 2244187, "self": 4252.85078458151, "children": { "RLTrainer._checkpoint": { "total": 8.353263096993032, "count": 64, "self": 8.353263096993032 } } }, "_update_policy": { "total": 5916.891660559005, "count": 1565, "self": 3666.2843281976784, "children": { "TorchPOCAOptimizer.update": { "total": 2250.6073323613264, "count": 46953, "self": 2250.6073323613264 } } } } } } }, "trainer_threads": { "total": 7.799972081556916e-07, "count": 1, "self": 7.799972081556916e-07 }, "TrainerController._save_models": { "total": 0.13704898099967977, "count": 1, "self": 0.0013844339991919696, "children": { "RLTrainer._checkpoint": { "total": 0.1356645470004878, "count": 1, "self": 0.1356645470004878 } } } } } } }