{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.145007848739624, "min": 3.113983154296875, "max": 3.2957377433776855, "count": 100 }, "SoccerTwos.Policy.Entropy.sum": { "value": 60786.7109375, "min": 24206.7578125, "max": 111993.65625, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 635.0, "min": 420.72727272727275, "max": 999.0, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 17780.0, "min": 14372.0, "max": 23580.0, "count": 100 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1212.7623810867292, "min": 1196.5799559406178, "max": 1214.483432000902, "count": 87 }, "SoccerTwos.Self-play.ELO.sum": { "value": 12127.623810867291, "min": 2395.689393922442, "max": 21759.380627156115, "count": 87 }, "SoccerTwos.Step.mean": { "value": 999549.0, "min": 9458.0, "max": 999549.0, "count": 100 }, "SoccerTwos.Step.sum": { "value": 999549.0, "min": 9458.0, "max": 999549.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.016431571915745735, "min": -0.024228036403656006, "max": 0.06398654729127884, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.24647358059883118, "min": -0.5330168008804321, "max": 0.9596019983291626, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.01908482052385807, "min": -0.030980387702584267, "max": 0.06391780078411102, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.2862723171710968, "min": -0.43372541666030884, "max": 0.9585136771202087, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.2940799991289775, "min": -0.6048266649246216, "max": 0.28345333139101664, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.411199986934662, "min": -9.072399973869324, "max": 6.454000078141689, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.2940799991289775, "min": -0.6048266649246216, "max": 0.28345333139101664, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.411199986934662, "min": -9.072399973869324, "max": 6.454000078141689, "count": 100 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015039970878084811, "min": 0.011326156100646282, "max": 0.021725554189955195, "count": 46 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015039970878084811, "min": 0.011326156100646282, "max": 0.021725554189955195, "count": 46 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0041566565011938415, "min": 0.0003892019973136485, "max": 0.007653002363319198, "count": 46 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0041566565011938415, "min": 0.0003892019973136485, "max": 0.007653002363319198, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.004163697858651479, "min": 0.00039171467251435387, "max": 0.008412215951830148, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.004163697858651479, "min": 0.00039171467251435387, "max": 0.008412215951830148, "count": 46 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 46 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 46 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 46 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 46 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704657743", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/nickmoran/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env ../SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704658981" }, "total": 1238.467857607, "count": 1, "self": 0.21909933899996759, "children": { "run_training.setup": { "total": 0.014572962999864103, "count": 1, "self": 0.014572962999864103 }, "TrainerController.start_learning": { "total": 1238.2341853050002, "count": 1, "self": 1.1365071440523025, "children": { "TrainerController._reset_env": { "total": 2.3054613570002402, "count": 5, "self": 2.3054613570002402 }, "TrainerController.advance": { "total": 1234.5921772929473, "count": 65068, "self": 1.0823352117495233, "children": { "env_step": { "total": 942.0232667091209, "count": 65068, "self": 674.3797625600787, "children": { "SubprocessEnvManager._take_step": { "total": 266.9369594030077, "count": 65068, "self": 6.5233603930196296, "children": { "TorchPolicy.evaluate": { "total": 260.41359900998805, "count": 129064, "self": 260.41359900998805 } } }, "workers": { "total": 0.706544746034524, "count": 65068, "self": 0.0, "children": { "worker_root": { "total": 1236.3593985579673, "count": 65068, "is_parallel": true, "self": 694.0215982799459, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003149805999782984, "count": 2, "is_parallel": true, "self": 0.0013695939996978268, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017802120000851573, "count": 8, "is_parallel": true, "self": 0.0017802120000851573 } } }, "UnityEnvironment.step": { "total": 0.020163213999694563, "count": 1, "is_parallel": true, "self": 0.00045288999945114483, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041599699989092187, "count": 1, "is_parallel": true, "self": 0.00041599699989092187 }, "communicator.exchange": { "total": 0.017734618999838858, "count": 1, "is_parallel": true, "self": 0.017734618999838858 }, "steps_from_proto": { "total": 0.0015597080005136377, "count": 2, "is_parallel": true, "self": 0.00027364100014892756, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012860670003647101, "count": 8, "is_parallel": true, "self": 0.0012860670003647101 } } } } } } }, "UnityEnvironment.step": { "total": 542.3315418720213, "count": 65067, "is_parallel": true, "self": 29.80501079610258, "children": { "UnityEnvironment._generate_step_input": { "total": 20.515231487978326, "count": 65067, "is_parallel": true, "self": 20.515231487978326 }, "communicator.exchange": { "total": 389.3101131680228, "count": 65067, "is_parallel": true, "self": 389.3101131680228 }, "steps_from_proto": { "total": 102.70118641991758, "count": 130134, "is_parallel": true, "self": 17.204724417928446, "children": { "_process_rank_one_or_two_observation": { "total": 85.49646200198913, "count": 520536, "is_parallel": true, "self": 85.49646200198913 } } } } }, "steps_from_proto": { "total": 0.006258406000142713, "count": 8, "is_parallel": true, "self": 0.0010369070005253889, "children": { "_process_rank_one_or_two_observation": { "total": 0.0052214989996173244, "count": 32, "is_parallel": true, "self": 0.0052214989996173244 } } } } } } } } }, "trainer_advance": { "total": 291.4865753720769, "count": 65068, "self": 8.949522493097447, "children": { "process_trajectory": { "total": 67.31413350897765, "count": 65068, "self": 66.92869954997741, "children": { "RLTrainer._checkpoint": { "total": 0.38543395900023825, "count": 2, "self": 0.38543395900023825 } } }, "_update_policy": { "total": 215.22291937000182, "count": 46, "self": 97.10910646900084, "children": { "TorchPOCAOptimizer.update": { "total": 118.11381290100098, "count": 1380, "self": 118.11381290100098 } } } } } } }, "trainer_threads": { "total": 6.440000106522348e-07, "count": 1, "self": 6.440000106522348e-07 }, "TrainerController._save_models": { "total": 0.20003886700033036, "count": 1, "self": 0.00118230800035235, "children": { "RLTrainer._checkpoint": { "total": 0.198856558999978, "count": 1, "self": 0.198856558999978 } } } } } } }