{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6265735626220703, "min": 1.5484353303909302, "max": 3.2956793308258057, "count": 1221 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34249.1328125, "min": 13981.4033203125, "max": 115104.0546875, "count": 1221 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 56.04597701149425, "min": 42.258620689655174, "max": 999.0, "count": 1221 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19504.0, "min": 11456.0, "max": 30252.0, "count": 1221 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1620.0417341444238, "min": 1196.3466733634127, "max": 1642.5166234869769, "count": 1215 }, "SoccerTwos.Self-play.ELO.sum": { "value": 281887.26174112974, "min": 2394.535852594916, "max": 358747.0237853759, "count": 1215 }, "SoccerTwos.Step.mean": { "value": 12209946.0, "min": 9142.0, "max": 12209946.0, "count": 1221 }, "SoccerTwos.Step.sum": { "value": 12209946.0, "min": 9142.0, "max": 12209946.0, "count": 1221 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.011582380160689354, "min": -0.12345093488693237, "max": 0.18368637561798096, "count": 1221 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.02691650390625, "min": -23.949481964111328, "max": 32.85422134399414, "count": 1221 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.007369144819676876, "min": -0.12794145941734314, "max": 0.18581099808216095, "count": 1221 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.2896003723144531, "min": -24.82064437866211, "max": 33.63179016113281, "count": 1221 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1221 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1221 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.05773142780576433, "min": -0.6875, "max": 0.5502645152230417, "count": 1221 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 10.102999866008759, "min": -61.78280007839203, "max": 68.23279988765717, "count": 1221 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.05773142780576433, "min": -0.6875, "max": 0.5502645152230417, "count": 1221 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 10.102999866008759, "min": -61.78280007839203, "max": 68.23279988765717, "count": 1221 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1221 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1221 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016578550640163787, "min": 0.010766705235194724, "max": 0.02550353014181989, "count": 590 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016578550640163787, "min": 0.010766705235194724, "max": 0.02550353014181989, "count": 590 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10681834295392037, "min": 0.0007180829411178517, "max": 0.12248274932305019, "count": 590 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10681834295392037, "min": 0.0007180829411178517, "max": 0.12248274932305019, "count": 590 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10834903717041015, "min": 0.0007234384558008363, "max": 0.12479151934385299, "count": 590 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10834903717041015, "min": 0.0007234384558008363, "max": 0.12479151934385299, "count": 590 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 590 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 590 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 590 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 590 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 590 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 590 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677412004", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Cereza\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1677451209" }, "total": 39204.465535, "count": 1, "self": 0.49378710000019055, "children": { "run_training.setup": { "total": 0.07150319999999999, "count": 1, "self": 0.07150319999999999 }, "TrainerController.start_learning": { "total": 39203.9002447, "count": 1, "self": 16.627648001129273, "children": { "TrainerController._reset_env": { "total": 7.107990100005867, "count": 62, "self": 7.107990100005867 }, "TrainerController.advance": { "total": 39180.00858479887, "count": 837499, "self": 15.177543395766406, "children": { "env_step": { "total": 11952.54620950334, "count": 837499, "self": 9220.515913203917, "children": { "SubprocessEnvManager._take_step": { "total": 2721.0198986993987, "count": 837499, "self": 92.35025679878026, "children": { "TorchPolicy.evaluate": { "total": 2628.6696419006184, "count": 1537658, "self": 2628.6696419006184 } } }, "workers": { "total": 11.01039760002432, "count": 837499, "self": 0.0, "children": { "worker_root": { "total": 39173.51721440323, "count": 837499, "is_parallel": true, "self": 31786.75880220276, "children": { "steps_from_proto": { "total": 0.10280219999157492, "count": 124, "is_parallel": true, "self": 0.018019800023632015, "children": { "_process_rank_one_or_two_observation": { "total": 0.0847823999679429, "count": 496, "is_parallel": true, "self": 0.0847823999679429 } } }, "UnityEnvironment.step": { "total": 7386.655610000482, "count": 837499, "is_parallel": true, "self": 425.4859668017907, "children": { "UnityEnvironment._generate_step_input": { "total": 347.03107059961445, "count": 837499, "is_parallel": true, "self": 347.03107059961445 }, "communicator.exchange": { "total": 5268.140466000155, "count": 837499, "is_parallel": true, "self": 5268.140466000155 }, "steps_from_proto": { "total": 1345.998106598921, "count": 1674998, "is_parallel": true, "self": 239.50459289770106, "children": { "_process_rank_one_or_two_observation": { "total": 1106.4935137012199, "count": 6699992, "is_parallel": true, "self": 1106.4935137012199 } } } } } } } } } } }, "trainer_advance": { "total": 27212.284831899764, "count": 837499, "self": 130.58228550038984, "children": { "process_trajectory": { "total": 4157.984527899309, "count": 837499, "self": 4155.143391799306, "children": { "RLTrainer._checkpoint": { "total": 2.8411361000028137, "count": 24, "self": 2.8411361000028137 } } }, "_update_policy": { "total": 22923.718018500065, "count": 590, "self": 1851.5352701003249, "children": { "TorchPOCAOptimizer.update": { "total": 21072.18274839974, "count": 17703, "self": 21072.18274839974 } } } } } } }, "trainer_threads": { "total": 8.999995770864189e-07, "count": 1, "self": 8.999995770864189e-07 }, "TrainerController._save_models": { "total": 0.1560209000017494, "count": 1, "self": 0.03218120000383351, "children": { "RLTrainer._checkpoint": { "total": 0.12383969999791589, "count": 1, "self": 0.12383969999791589 } } } } } } }