{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9432116746902466, "min": 1.9432116746902466, "max": 3.295809507369995, "count": 499 }, "SoccerTwos.Policy.Entropy.sum": { "value": 39423.87890625, "min": 13132.7099609375, "max": 107870.765625, "count": 499 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 50.302083333333336, "min": 43.095652173913045, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19316.0, "min": 8672.0, "max": 31624.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1674.02855869572, "min": 1196.286910117156, "max": 1679.6190556058052, "count": 495 }, "SoccerTwos.Self-play.ELO.sum": { "value": 321413.48326957825, "min": 2392.573820234312, "max": 364821.9619331358, "count": 495 }, "SoccerTwos.Step.mean": { "value": 4999968.0, "min": 9830.0, "max": 4999968.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999968.0, "min": 9830.0, "max": 4999968.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.007032178342342377, "min": -0.04914279282093048, "max": 0.35222893953323364, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.3501782417297363, "min": -8.698274612426758, "max": 66.21903991699219, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.004948621150106192, "min": -0.05219143629074097, "max": 0.3570581376552582, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.9501352310180664, "min": -9.237884521484375, "max": 67.1269302368164, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.08601249816517036, "min": -0.6534099996089935, "max": 0.7964852481591896, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -16.514399647712708, "min": -48.28880035877228, "max": 143.60980010032654, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.08601249816517036, "min": -0.6534099996089935, "max": 0.7964852481591896, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -16.514399647712708, "min": -48.28880035877228, "max": 143.60980010032654, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019628474997201315, "min": 0.011466718542700012, "max": 0.027396725938888266, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019628474997201315, "min": 0.011466718542700012, "max": 0.027396725938888266, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10348925118645032, "min": 0.00036750142632323936, "max": 0.11177791555722555, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10348925118645032, "min": 0.00036750142632323936, "max": 0.11177791555722555, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10467774420976639, "min": 0.0003705531096784398, "max": 0.11403980230291684, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10467774420976639, "min": 0.0003705531096784398, "max": 0.11403980230291684, "count": 239 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 239 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 239 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679607783", "python_version": "3.9.0 (tags/v3.9.0:9cf6752, Oct 5 2020, 15:34:40) [MSC v.1927 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Kevin\\Desktop\\Kevin\\1-Courses\\4-Machine Learning\\local\\Scripts\\mlagents-learn ./ml-agents/config/poca/SoccerTwos.yaml --env=./ml-agents/SoccerTwos/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": "2.0.0+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1679625606" }, "total": 17822.9921143, "count": 1, "self": 0.3079911999993783, "children": { "run_training.setup": { "total": 0.10757620000000001, "count": 1, "self": 0.10757620000000001 }, "TrainerController.start_learning": { "total": 17822.5765469, "count": 1, "self": 7.27636779995737, "children": { "TrainerController._reset_env": { "total": 4.166740800000428, "count": 13, "self": 4.166740800000428 }, "TrainerController.advance": { "total": 17810.967975700045, "count": 337791, "self": 6.090069999539992, "children": { "env_step": { "total": 6309.058717699814, "count": 337791, "self": 4771.151907200039, "children": { "SubprocessEnvManager._take_step": { "total": 1533.2260016004439, "count": 337791, "self": 41.41981320073933, "children": { "TorchPolicy.evaluate": { "total": 1491.8061883997045, "count": 627840, "self": 1491.8061883997045 } } }, "workers": { "total": 4.680808899331087, "count": 337791, "self": 0.0, "children": { "worker_root": { "total": 17805.052527699896, "count": 337791, "is_parallel": true, "self": 13938.121051799852, "children": { "steps_from_proto": { "total": 0.025178899995337733, "count": 26, "is_parallel": true, "self": 0.004867599982018245, "children": { "_process_rank_one_or_two_observation": { "total": 0.02031130001331949, "count": 104, "is_parallel": true, "self": 0.02031130001331949 } } }, "UnityEnvironment.step": { "total": 3866.906297000048, "count": 337791, "is_parallel": true, "self": 186.6947712011456, "children": { "UnityEnvironment._generate_step_input": { "total": 148.74864609967014, "count": 337791, "is_parallel": true, "self": 148.74864609967014 }, "communicator.exchange": { "total": 2921.1069610990367, "count": 337791, "is_parallel": true, "self": 2921.1069610990367 }, "steps_from_proto": { "total": 610.3559186001955, "count": 675582, "is_parallel": true, "self": 120.20027779864427, "children": { "_process_rank_one_or_two_observation": { "total": 490.1556408015513, "count": 2702328, "is_parallel": true, "self": 490.1556408015513 } } } } } } } } } } }, "trainer_advance": { "total": 11495.81918800069, "count": 337791, "self": 53.293387100568, "children": { "process_trajectory": { "total": 1730.304559000122, "count": 337791, "self": 1728.4134495001229, "children": { "RLTrainer._checkpoint": { "total": 1.8911094999991747, "count": 10, "self": 1.8911094999991747 } } }, "_update_policy": { "total": 9712.2212419, "count": 239, "self": 759.1933382000134, "children": { "TorchPOCAOptimizer.update": { "total": 8953.027903699987, "count": 7182, "self": 8953.027903699987 } } } } } } }, "trainer_threads": { "total": 7.999988156370819e-07, "count": 1, "self": 7.999988156370819e-07 }, "TrainerController._save_models": { "total": 0.16546179999932065, "count": 1, "self": 0.0039034999972500373, "children": { "RLTrainer._checkpoint": { "total": 0.1615583000020706, "count": 1, "self": 0.1615583000020706 } } } } } } }