{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8314324617385864, "min": 1.789159893989563, "max": 3.295753002166748, "count": 901 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34811.8671875, "min": 5687.85009765625, "max": 149578.171875, "count": 901 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 48.78, "min": 37.57251908396947, "max": 999.0, "count": 901 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19512.0, "min": 4040.0, "max": 33772.0, "count": 901 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1517.3965850324282, "min": 1184.267922786178, "max": 1548.2740265827172, "count": 853 }, "SoccerTwos.Self-play.ELO.sum": { "value": 303479.31700648565, "min": 2368.535845572356, "max": 384956.78245914215, "count": 853 }, "SoccerTwos.Step.mean": { "value": 9009987.0, "min": 9422.0, "max": 9009987.0, "count": 901 }, "SoccerTwos.Step.sum": { "value": 9009987.0, "min": 9422.0, "max": 9009987.0, "count": 901 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.035350676625967026, "min": -0.16072148084640503, "max": 0.1682451069355011, "count": 901 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 7.105485916137695, "min": -25.393993377685547, "max": 24.404903411865234, "count": 901 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.03739427030086517, "min": -0.15999765694141388, "max": 0.1723681092262268, "count": 901 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 7.51624870300293, "min": -25.27962875366211, "max": 24.359254837036133, "count": 901 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 901 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 901 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.15444577214729727, "min": -0.5216319990158081, "max": 0.40232940982369814, "count": 901 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 31.04360020160675, "min": -51.80359983444214, "max": 60.683199882507324, "count": 901 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.15444577214729727, "min": -0.5216319990158081, "max": 0.40232940982369814, "count": 901 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 31.04360020160675, "min": -51.80359983444214, "max": 60.683199882507324, "count": 901 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 901 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 901 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01932770558317619, "min": 0.01121681028259142, "max": 0.026336382719940352, "count": 430 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01932770558317619, "min": 0.01121681028259142, "max": 0.026336382719940352, "count": 430 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10662107244133949, "min": 9.917254737956683e-06, "max": 0.12936393395066262, "count": 430 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10662107244133949, "min": 9.917254737956683e-06, "max": 0.12936393395066262, "count": 430 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10795135920246442, "min": 1.0266141589454492e-05, "max": 0.13113280634085336, "count": 430 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10795135920246442, "min": 1.0266141589454492e-05, "max": 0.13113280634085336, "count": 430 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 430 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 430 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 430 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 430 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 430 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 430 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1683926873", "python_version": "3.9.16 (main, Mar 8 2023, 04:29:24) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/lennart/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.app --run-id=SoccerTwos2 --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", "numpy_version": "1.21.2", "end_time_seconds": "1683959442" }, "total": 32568.760720458, "count": 1, "self": 0.1430255830018723, "children": { "run_training.setup": { "total": 0.012801750000000056, "count": 1, "self": 0.012801750000000056 }, "TrainerController.start_learning": { "total": 32568.604893125, "count": 1, "self": 6.341404016075103, "children": { "TrainerController._reset_env": { "total": 4.145923248990697, "count": 52, "self": 4.145923248990697 }, "TrainerController.advance": { "total": 32558.03919919294, "count": 614483, "self": 5.69787183410881, "children": { "env_step": { "total": 26301.003836776035, "count": 614483, "self": 25376.330136111632, "children": { "SubprocessEnvManager._take_step": { "total": 920.0733070286193, "count": 614483, "self": 26.157878263396356, "children": { "TorchPolicy.evaluate": { "total": 893.9154287652229, "count": 1144798, "self": 893.9154287652229 } } }, "workers": { "total": 4.600393635782806, "count": 614483, "self": 0.0, "children": { "worker_root": { "total": 32552.665807487978, "count": 614483, "is_parallel": true, "self": 7960.602729470884, "children": { "steps_from_proto": { "total": 0.07710608401059571, "count": 104, "is_parallel": true, "self": 0.00842724294969388, "children": { "_process_rank_one_or_two_observation": { "total": 0.06867884106090183, "count": 416, "is_parallel": true, "self": 0.06867884106090183 } } }, "UnityEnvironment.step": { "total": 24591.985971933085, "count": 614483, "is_parallel": true, "self": 65.47776982933647, "children": { "UnityEnvironment._generate_step_input": { "total": 431.08953150978243, "count": 614483, "is_parallel": true, "self": 431.08953150978243 }, "communicator.exchange": { "total": 23150.398963985284, "count": 614483, "is_parallel": true, "self": 23150.398963985284 }, "steps_from_proto": { "total": 945.0197066086791, "count": 1228966, "is_parallel": true, "self": 98.54841948091416, "children": { "_process_rank_one_or_two_observation": { "total": 846.471287127765, "count": 4915864, "is_parallel": true, "self": 846.471287127765 } } } } } } } } } } }, "trainer_advance": { "total": 6251.337490582794, "count": 614483, "self": 52.52695570535525, "children": { "process_trajectory": { "total": 1327.657086051442, "count": 614483, "self": 1326.224164923438, "children": { "RLTrainer._checkpoint": { "total": 1.4329211280041818, "count": 18, "self": 1.4329211280041818 } } }, "_update_policy": { "total": 4871.153448825997, "count": 431, "self": 682.423660740842, "children": { "TorchPOCAOptimizer.update": { "total": 4188.729788085155, "count": 12918, "self": 4188.729788085155 } } } } } } }, "trainer_threads": { "total": 5.419969966169447e-07, "count": 1, "self": 5.419969966169447e-07 }, "TrainerController._save_models": { "total": 0.07836612499886542, "count": 1, "self": 0.0007490419993700925, "children": { "RLTrainer._checkpoint": { "total": 0.07761708299949532, "count": 1, "self": 0.07761708299949532 } } } } } } }