{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2882423400878906, "min": 3.28551983833313, "max": 3.2957446575164795, "count": 4 }, "SoccerTwos.Policy.Entropy.sum": { "value": 67974.546875, "min": 61610.06640625, "max": 105463.828125, "count": 4 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 609.375, "min": 605.1, "max": 889.1666666666666, "count": 4 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19500.0, "min": 16868.0, "max": 24204.0, "count": 4 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1203.861183788245, "min": 1200.7468599944746, "max": 1203.9485920570594, "count": 4 }, "SoccerTwos.Self-play.ELO.sum": { "value": 12038.611837882449, "min": 2407.8971841141188, "max": 14408.962319933695, "count": 4 }, "SoccerTwos.Step.mean": { "value": 39014.0, "min": 9122.0, "max": 39014.0, "count": 4 }, "SoccerTwos.Step.sum": { "value": 39014.0, "min": 9122.0, "max": 39014.0, "count": 4 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.03001139871776104, "min": 0.028771625831723213, "max": 0.03587218374013901, "count": 4 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.48018237948417664, "min": 0.3164878785610199, "max": 0.6098271012306213, "count": 4 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.035965994000434875, "min": 0.03436855971813202, "max": 0.035965994000434875, "count": 4 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.575455904006958, "min": 0.3780541718006134, "max": 0.6097903251647949, "count": 4 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 4 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 4 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.19109999760985374, "min": -0.2727272727272727, "max": 0.19109999760985374, "count": 4 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 3.05759996175766, "min": -3.0, "max": 3.05759996175766, "count": 4 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.19109999760985374, "min": -0.2727272727272727, "max": 0.19109999760985374, "count": 4 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 3.05759996175766, "min": -3.0, "max": 3.05759996175766, "count": 4 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01626398858303825, "min": 0.01626398858303825, "max": 0.01626398858303825, "count": 1 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01626398858303825, "min": 0.01626398858303825, "max": 0.01626398858303825, "count": 1 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0046758413780480625, "min": 0.0046758413780480625, "max": 0.0046758413780480625, "count": 1 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0046758413780480625, "min": 0.0046758413780480625, "max": 0.0046758413780480625, "count": 1 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.004306589548165599, "min": 0.004306589548165599, "max": 0.004306589548165599, "count": 1 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.004306589548165599, "min": 0.004306589548165599, "max": 0.004306589548165599, "count": 1 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1711608727", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/node/WORK/WORKSPACE/ENVS/miscs/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./trained-envs-executables/linux/SoccerTwos.x86_64 --run-id=SoccerTwos --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711608804" }, "total": 76.68805835700005, "count": 1, "self": 0.004073394999068114, "children": { "run_training.setup": { "total": 0.018470230001184973, "count": 1, "self": 0.018470230001184973 }, "TrainerController.start_learning": { "total": 76.66551473199979, "count": 1, "self": 0.06454389196915145, "children": { "TrainerController._reset_env": { "total": 4.520945236999978, "count": 1, "self": 4.520945236999978 }, "TrainerController.advance": { "total": 71.92138248802985, "count": 3128, "self": 0.053513976990871015, "children": { "env_step": { "total": 44.710160134034595, "count": 3128, "self": 35.7539417990356, "children": { "SubprocessEnvManager._take_step": { "total": 8.921819937015243, "count": 3128, "self": 0.2753146980085148, "children": { "TorchPolicy.evaluate": { "total": 8.646505239006729, "count": 6218, "self": 8.646505239006729 } } }, "workers": { "total": 0.03439839798375033, "count": 3128, "self": 0.0, "children": { "worker_root": { "total": 68.89855089398225, "count": 3128, "is_parallel": true, "self": 39.51162345092598, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017805160005082143, "count": 2, "is_parallel": true, "self": 0.00041291399975307286, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013676020007551415, "count": 8, "is_parallel": true, "self": 0.0013676020007551415 } } }, "UnityEnvironment.step": { "total": 0.031287859999793, "count": 1, "is_parallel": true, "self": 0.00043526400077098515, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005393470000853995, "count": 1, "is_parallel": true, "self": 0.0005393470000853995 }, "communicator.exchange": { "total": 0.028965359000721946, "count": 1, "is_parallel": true, "self": 0.028965359000721946 }, "steps_from_proto": { "total": 0.0013478899982146686, "count": 2, "is_parallel": true, "self": 0.00027469300221127924, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010731969960033894, "count": 8, "is_parallel": true, "self": 0.0010731969960033894 } } } } } } }, "UnityEnvironment.step": { "total": 29.386927443056265, "count": 3127, "is_parallel": true, "self": 1.519220111955292, "children": { "UnityEnvironment._generate_step_input": { "total": 1.035092900019663, "count": 3127, "is_parallel": true, "self": 1.035092900019663 }, "communicator.exchange": { "total": 21.991858610033887, "count": 3127, "is_parallel": true, "self": 21.991858610033887 }, "steps_from_proto": { "total": 4.8407558210474235, "count": 6254, "is_parallel": true, "self": 0.9229285281289776, "children": { "_process_rank_one_or_two_observation": { "total": 3.917827292918446, "count": 25016, "is_parallel": true, "self": 3.917827292918446 } } } } } } } } } } }, "trainer_advance": { "total": 27.157708377004383, "count": 3128, "self": 0.48069884398864815, "children": { "process_trajectory": { "total": 4.613371938014097, "count": 3128, "self": 4.613371938014097 }, "_update_policy": { "total": 22.063637595001637, "count": 2, "self": 3.437678854994374, "children": { "TorchPOCAOptimizer.update": { "total": 18.625958740007263, "count": 44, "self": 18.625958740007263 } } } } } } }, "trainer_threads": { "total": 1.0200001270277426e-06, "count": 1, "self": 1.0200001270277426e-06 }, "TrainerController._save_models": { "total": 0.15864209500068682, "count": 1, "self": 0.0011822640008176677, "children": { "RLTrainer._checkpoint": { "total": 0.15745983099986915, "count": 1, "self": 0.15745983099986915 } } } } } } }