{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8196464776992798, "min": 1.7705482244491577, "max": 3.295736789703369, "count": 815 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37441.046875, "min": 11857.4052734375, "max": 130598.53125, "count": 815 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 50.608247422680414, "min": 40.186440677966104, "max": 999.0, "count": 815 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19636.0, "min": 16228.0, "max": 23844.0, "count": 815 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1551.1802826727808, "min": 1187.6667522950163, "max": 1559.5549396170543, "count": 747 }, "SoccerTwos.Self-play.ELO.sum": { "value": 300928.97483851947, "min": 2375.3335045900326, "max": 359461.06313298026, "count": 747 }, "SoccerTwos.Step.mean": { "value": 8149973.0, "min": 9288.0, "max": 8149973.0, "count": 815 }, "SoccerTwos.Step.sum": { "value": 8149973.0, "min": 9288.0, "max": 8149973.0, "count": 815 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.03639158979058266, "min": -0.13772551715373993, "max": 0.23058919608592987, "count": 815 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 6.987185478210449, "min": -21.622905731201172, "max": 28.593059539794922, "count": 815 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.03962581977248192, "min": -0.1361798793077469, "max": 0.2292519211769104, "count": 815 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 7.608157634735107, "min": -21.38024139404297, "max": 28.42723846435547, "count": 815 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 815 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 815 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.017775001004338264, "min": -0.5959034479897598, "max": 0.5912790332109698, "count": 815 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 3.4128001928329468, "min": -53.94319999217987, "max": 73.31860011816025, "count": 815 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.017775001004338264, "min": -0.5959034479897598, "max": 0.5912790332109698, "count": 815 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 3.4128001928329468, "min": -53.94319999217987, "max": 73.31860011816025, "count": 815 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 815 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 815 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014307073920887585, "min": 0.009577089563633005, "max": 0.024101764877559616, "count": 389 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014307073920887585, "min": 0.009577089563633005, "max": 0.024101764877559616, "count": 389 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11183047691980998, "min": 1.9586536912659843e-06, "max": 0.12080309763550759, "count": 389 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11183047691980998, "min": 1.9586536912659843e-06, "max": 0.12080309763550759, "count": 389 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.113816549628973, "min": 2.6621701313918797e-06, "max": 0.12344175701340039, "count": 389 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.113816549628973, "min": 2.6621701313918797e-06, "max": 0.12344175701340039, "count": 389 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 389 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 389 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 389 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 389 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 389 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 389 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704364596", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos --run-id=SoccerTwos --no-graphics", "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": "1704382856" }, "total": 18259.477593715998, "count": 1, "self": 0.13598439499764936, "children": { "run_training.setup": { "total": 0.08484182600000167, "count": 1, "self": 0.08484182600000167 }, "TrainerController.start_learning": { "total": 18259.256767495, "count": 1, "self": 12.969908614239102, "children": { "TrainerController._reset_env": { "total": 5.089623655004743, "count": 33, "self": 5.089623655004743 }, "TrainerController.advance": { "total": 18240.64273338476, "count": 549792, "self": 13.796349829030078, "children": { "env_step": { "total": 14461.216845018133, "count": 549792, "self": 11141.949741455857, "children": { "SubprocessEnvManager._take_step": { "total": 3311.4527992548165, "count": 549792, "self": 92.60211251819874, "children": { "TorchPolicy.evaluate": { "total": 3218.8506867366177, "count": 1033100, "self": 3218.8506867366177 } } }, "workers": { "total": 7.814304307458713, "count": 549791, "self": 0.0, "children": { "worker_root": { "total": 18225.78170096431, "count": 549791, "is_parallel": true, "self": 8850.038199256865, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0051195770000163066, "count": 2, "is_parallel": true, "self": 0.0031226919999767233, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019968850000395832, "count": 8, "is_parallel": true, "self": 0.0019968850000395832 } } }, "UnityEnvironment.step": { "total": 0.05129523099998323, "count": 1, "is_parallel": true, "self": 0.0012138540000137255, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008943259999796283, "count": 1, "is_parallel": true, "self": 0.0008943259999796283 }, "communicator.exchange": { "total": 0.045129342999985056, "count": 1, "is_parallel": true, "self": 0.045129342999985056 }, "steps_from_proto": { "total": 0.004057708000004823, "count": 2, "is_parallel": true, "self": 0.0007009910000874697, "children": { "_process_rank_one_or_two_observation": { "total": 0.003356716999917353, "count": 8, "is_parallel": true, "self": 0.003356716999917353 } } } } } } }, "UnityEnvironment.step": { "total": 9375.66795970344, "count": 549790, "is_parallel": true, "self": 621.4516622860046, "children": { "UnityEnvironment._generate_step_input": { "total": 409.2889280078055, "count": 549790, "is_parallel": true, "self": 409.2889280078055 }, "communicator.exchange": { "total": 6417.927065927161, "count": 549790, "is_parallel": true, "self": 6417.927065927161 }, "steps_from_proto": { "total": 1927.0003034824704, "count": 1099580, "is_parallel": true, "self": 312.77393050615615, "children": { "_process_rank_one_or_two_observation": { "total": 1614.2263729763142, "count": 4398320, "is_parallel": true, "self": 1614.2263729763142 } } } } }, "steps_from_proto": { "total": 0.07554200400613809, "count": 64, "is_parallel": true, "self": 0.01562944801071353, "children": { "_process_rank_one_or_two_observation": { "total": 0.059912555995424555, "count": 256, "is_parallel": true, "self": 0.059912555995424555 } } } } } } } } }, "trainer_advance": { "total": 3765.6295385375993, "count": 549791, "self": 105.73242453624744, "children": { "process_trajectory": { "total": 1504.6074512073426, "count": 549791, "self": 1501.1624245823414, "children": { "RLTrainer._checkpoint": { "total": 3.445026625001219, "count": 16, "self": 3.445026625001219 } } }, "_update_policy": { "total": 2155.289662794009, "count": 390, "self": 1255.0950127390029, "children": { "TorchPOCAOptimizer.update": { "total": 900.194650055006, "count": 11700, "self": 900.194650055006 } } } } } } }, "trainer_threads": { "total": 1.41999771585688e-06, "count": 1, "self": 1.41999771585688e-06 }, "TrainerController._save_models": { "total": 0.5545004209998297, "count": 1, "self": 0.00698675600142451, "children": { "RLTrainer._checkpoint": { "total": 0.5475136649984051, "count": 1, "self": 0.5475136649984051 } } } } } } }