{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.50038480758667, "min": 1.4463025331497192, "max": 3.2957005500793457, "count": 1951 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30487.8203125, "min": 18397.40625, "max": 158768.234375, "count": 1951 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 61.160493827160494, "min": 41.63793103448276, "max": 999.0, "count": 1951 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19816.0, "min": 14264.0, "max": 27236.0, "count": 1951 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1662.573386692991, "min": 1187.7017999143338, "max": 1703.9293699092589, "count": 1944 }, "SoccerTwos.Self-play.ELO.sum": { "value": 269336.88864426455, "min": 2376.7834953756137, "max": 377645.862949851, "count": 1944 }, "SoccerTwos.Step.mean": { "value": 19509902.0, "min": 9634.0, "max": 19509902.0, "count": 1951 }, "SoccerTwos.Step.sum": { "value": 19509902.0, "min": 9634.0, "max": 19509902.0, "count": 1951 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.004716084338724613, "min": -0.13077238202095032, "max": 0.23248226940631866, "count": 1951 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.7640056610107422, "min": -26.023704528808594, "max": 27.897872924804688, "count": 1951 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0025035864673554897, "min": -0.13233692944049835, "max": 0.23026040196418762, "count": 1951 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.405580997467041, "min": -26.33504867553711, "max": 27.631248474121094, "count": 1951 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1951 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1951 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0590913560655382, "min": -0.5454545454545454, "max": 0.49807326569415555, "count": 1951 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 9.572799682617188, "min": -62.55239987373352, "max": 52.70700013637543, "count": 1951 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0590913560655382, "min": -0.5454545454545454, "max": 0.49807326569415555, "count": 1951 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 9.572799682617188, "min": -62.55239987373352, "max": 52.70700013637543, "count": 1951 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1951 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1951 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.0203987649991177, "min": 0.010457840793969808, "max": 0.025209849560633303, "count": 945 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0203987649991177, "min": 0.010457840793969808, "max": 0.025209849560633303, "count": 945 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10580266863107682, "min": 0.00023729713696714802, "max": 0.1228718139231205, "count": 945 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10580266863107682, "min": 0.00023729713696714802, "max": 0.1228718139231205, "count": 945 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10765738462408384, "min": 0.00024293343982814501, "max": 0.12517891004681586, "count": 945 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10765738462408384, "min": 0.00024293343982814501, "max": 0.12517891004681586, "count": 945 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 945 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 945 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 945 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 945 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 945 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 945 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676901432", "python_version": "3.9.16 (main, Jan 11 2023, 16:05:54) \n[GCC 11.2.0]", "command_line_arguments": "/home/besa/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1", "numpy_version": "1.21.2", "end_time_seconds": "1676923073" }, "total": 21640.979151537, "count": 1, "self": 0.1469642060037586, "children": { "run_training.setup": { "total": 0.007614835999902425, "count": 1, "self": 0.007614835999902425 }, "TrainerController.start_learning": { "total": 21640.824572495, "count": 1, "self": 26.142664178252744, "children": { "TrainerController._reset_env": { "total": 3.028352016009876, "count": 98, "self": 3.028352016009876 }, "TrainerController.advance": { "total": 21611.53240772474, "count": 1343175, "self": 25.12081788350406, "children": { "env_step": { "total": 15813.638102928096, "count": 1343175, "self": 11907.680019729087, "children": { "SubprocessEnvManager._take_step": { "total": 3889.6485960010004, "count": 1343175, "self": 112.11267394682454, "children": { "TorchPolicy.evaluate": { "total": 3777.535922054176, "count": 2453406, "self": 3777.535922054176 } } }, "workers": { "total": 16.309487198009492, "count": 1343174, "self": 0.0, "children": { "worker_root": { "total": 21612.656639202512, "count": 1343174, "is_parallel": true, "self": 12094.475062970465, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017050439998911315, "count": 2, "is_parallel": true, "self": 0.00046933500016166363, "children": { "_process_rank_one_or_two_observation": { "total": 0.001235708999729468, "count": 8, "is_parallel": true, "self": 0.001235708999729468 } } }, "UnityEnvironment.step": { "total": 0.02268114899993634, "count": 1, "is_parallel": true, "self": 0.00046165399999154033, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034718300003078184, "count": 1, "is_parallel": true, "self": 0.00034718300003078184 }, "communicator.exchange": { "total": 0.020472824999842487, "count": 1, "is_parallel": true, "self": 0.020472824999842487 }, "steps_from_proto": { "total": 0.001399487000071531, "count": 2, "is_parallel": true, "self": 0.0002858620000552037, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011136250000163272, "count": 8, "is_parallel": true, "self": 0.0011136250000163272 } } } } } } }, "UnityEnvironment.step": { "total": 9518.028528892033, "count": 1343173, "is_parallel": true, "self": 566.6882429159596, "children": { "UnityEnvironment._generate_step_input": { "total": 352.21802995038206, "count": 1343173, "is_parallel": true, "self": 352.21802995038206 }, "communicator.exchange": { "total": 6962.769831656675, "count": 1343173, "is_parallel": true, "self": 6962.769831656675 }, "steps_from_proto": { "total": 1636.3524243690176, "count": 2686346, "is_parallel": true, "self": 317.62920514360985, "children": { "_process_rank_one_or_two_observation": { "total": 1318.7232192254078, "count": 10745384, "is_parallel": true, "self": 1318.7232192254078 } } } } }, "steps_from_proto": { "total": 0.15304734001392717, "count": 194, "is_parallel": true, "self": 0.030386975050532783, "children": { "_process_rank_one_or_two_observation": { "total": 0.12266036496339439, "count": 776, "is_parallel": true, "self": 0.12266036496339439 } } } } } } } } }, "trainer_advance": { "total": 5772.773486913136, "count": 1343174, "self": 185.6607692266134, "children": { "process_trajectory": { "total": 2217.7470853194845, "count": 1343174, "self": 2213.118357621486, "children": { "RLTrainer._checkpoint": { "total": 4.628727697998329, "count": 39, "self": 4.628727697998329 } } }, "_update_policy": { "total": 3369.3656323670384, "count": 945, "self": 1959.0800218040945, "children": { "TorchPOCAOptimizer.update": { "total": 1410.285610562944, "count": 28353, "self": 1410.285610562944 } } } } } } }, "trainer_threads": { "total": 1.8860009731724858e-06, "count": 1, "self": 1.8860009731724858e-06 }, "TrainerController._save_models": { "total": 0.12114668999856804, "count": 1, "self": 0.0012847439975303132, "children": { "RLTrainer._checkpoint": { "total": 0.11986194600103772, "count": 1, "self": 0.11986194600103772 } } } } } } }