{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.971757173538208, "min": 1.9702214002609253, "max": 3.295745611190796, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36469.62109375, "min": 26095.61328125, "max": 152529.375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.08888888888889, "min": 39.642276422764226, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19472.0, "min": 16396.0, "max": 24236.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1505.933671931044, "min": 1198.025705444381, "max": 1510.0504699204894, "count": 469 }, "SoccerTwos.Self-play.ELO.sum": { "value": 271068.06094758795, "min": 2400.5182950146723, "max": 363117.00495893107, "count": 469 }, "SoccerTwos.Step.mean": { "value": 4999952.0, "min": 9134.0, "max": 4999952.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999952.0, "min": 9134.0, "max": 4999952.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0018862575525417924, "min": -0.1087125912308693, "max": 0.1725998818874359, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.33952635526657104, "min": -26.634584426879883, "max": 27.78858184814453, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0015606041997671127, "min": -0.1133226677775383, "max": 0.17355959117412567, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.2809087634086609, "min": -27.764053344726562, "max": 27.72662353515625, "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": 0.04498777952459124, "min": -0.5398857146501541, "max": 0.5801333226263523, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 8.097800314426422, "min": -64.95680010318756, "max": 54.01600044965744, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.04498777952459124, "min": -0.5398857146501541, "max": 0.5801333226263523, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 8.097800314426422, "min": -64.95680010318756, "max": 54.01600044965744, "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": 0.01639594529212142, "min": 0.011375034862430767, "max": 0.024761093304065677, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01639594529212142, "min": 0.011375034862430767, "max": 0.024761093304065677, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10465365772445996, "min": 2.314404673597892e-06, "max": 0.11985040878256162, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10465365772445996, "min": 2.314404673597892e-06, "max": 0.11985040878256162, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10639850174387296, "min": 2.2251761189788036e-06, "max": 0.12240360130866369, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10639850174387296, "min": 2.2251761189788036e-06, "max": 0.12240360130866369, "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": 0.20000000000000007, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 239 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 239 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688571562", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn --force ./ml-agents/config/poca/SoccerTwos.yaml --env=./ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --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": "1.11.0+cu115", "numpy_version": "1.21.2", "end_time_seconds": "1688580354" }, "total": 8792.130980844, "count": 1, "self": 0.32373556700076733, "children": { "run_training.setup": { "total": 0.03959353300001567, "count": 1, "self": 0.03959353300001567 }, "TrainerController.start_learning": { "total": 8791.767651744, "count": 1, "self": 6.655949540985603, "children": { "TrainerController._reset_env": { "total": 6.885630088994958, "count": 25, "self": 6.885630088994958 }, "TrainerController.advance": { "total": 8777.989917254017, "count": 340349, "self": 6.959609317264039, "children": { "env_step": { "total": 6676.239928678801, "count": 340349, "self": 4907.813310475121, "children": { "SubprocessEnvManager._take_step": { "total": 1764.5325698936379, "count": 340349, "self": 51.249021445286644, "children": { "TorchPolicy.evaluate": { "total": 1713.2835484483512, "count": 634278, "self": 1713.2835484483512 } } }, "workers": { "total": 3.8940483100425354, "count": 340349, "self": 0.0, "children": { "worker_root": { "total": 8779.436202104116, "count": 340349, "is_parallel": true, "self": 4672.470853867153, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00294004300008055, "count": 2, "is_parallel": true, "self": 0.0007945350005229557, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021455079995575943, "count": 8, "is_parallel": true, "self": 0.0021455079995575943 } } }, "UnityEnvironment.step": { "total": 0.031158214000015505, "count": 1, "is_parallel": true, "self": 0.0006777199998850847, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005000779999591032, "count": 1, "is_parallel": true, "self": 0.0005000779999591032 }, "communicator.exchange": { "total": 0.027809690000140108, "count": 1, "is_parallel": true, "self": 0.027809690000140108 }, "steps_from_proto": { "total": 0.002170726000031209, "count": 2, "is_parallel": true, "self": 0.00040949699973680254, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017612290002944064, "count": 8, "is_parallel": true, "self": 0.0017612290002944064 } } } } } } }, "UnityEnvironment.step": { "total": 4106.914589042968, "count": 340348, "is_parallel": true, "self": 202.76129913838122, "children": { "UnityEnvironment._generate_step_input": { "total": 125.19263645896103, "count": 340348, "is_parallel": true, "self": 125.19263645896103 }, "communicator.exchange": { "total": 3141.4161885170834, "count": 340348, "is_parallel": true, "self": 3141.4161885170834 }, "steps_from_proto": { "total": 637.544464928543, "count": 680696, "is_parallel": true, "self": 119.00165214230174, "children": { "_process_rank_one_or_two_observation": { "total": 518.5428127862413, "count": 2722784, "is_parallel": true, "self": 518.5428127862413 } } } } }, "steps_from_proto": { "total": 0.050759193994963425, "count": 48, "is_parallel": true, "self": 0.009249178002846747, "children": { "_process_rank_one_or_two_observation": { "total": 0.04151001599211668, "count": 192, "is_parallel": true, "self": 0.04151001599211668 } } } } } } } } }, "trainer_advance": { "total": 2094.7903792579523, "count": 340349, "self": 56.484258983399286, "children": { "process_trajectory": { "total": 877.0320136615542, "count": 340349, "self": 874.5822189055539, "children": { "RLTrainer._checkpoint": { "total": 2.4497947560003013, "count": 10, "self": 2.4497947560003013 } } }, "_update_policy": { "total": 1161.2741066129988, "count": 239, "self": 813.95436433497, "children": { "TorchPOCAOptimizer.update": { "total": 347.3197422780288, "count": 7170, "self": 347.3197422780288 } } } } } } }, "trainer_threads": { "total": 9.89000909612514e-07, "count": 1, "self": 9.89000909612514e-07 }, "TrainerController._save_models": { "total": 0.2361538710010791, "count": 1, "self": 0.0017686020019027637, "children": { "RLTrainer._checkpoint": { "total": 0.23438526899917633, "count": 1, "self": 0.23438526899917633 } } } } } } }