{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.7609968185424805, "min": 2.759597063064575, "max": 3.2947139739990234, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 53011.140625, "min": 23319.828125, "max": 130506.2890625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 64.34210526315789, "min": 60.525, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19560.0, "min": 3996.0, "max": 30808.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1426.7027287832227, "min": 1198.430818454253, "max": 1458.5056356146274, "count": 492 }, "SoccerTwos.Self-play.ELO.sum": { "value": 216858.81477504986, "min": 2401.4985608882907, "max": 229114.54091223533, "count": 492 }, "SoccerTwos.Step.mean": { "value": 4999968.0, "min": 9420.0, "max": 4999968.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999968.0, "min": 9420.0, "max": 4999968.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0476294569671154, "min": -0.1635277420282364, "max": 0.1583396941423416, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 7.287306785583496, "min": -18.06836700439453, "max": 22.167556762695312, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.044529274106025696, "min": -0.19693352282047272, "max": 0.1574898660182953, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 6.812979221343994, "min": -18.4958553314209, "max": 22.048582077026367, "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": 0.10239608147565056, "min": -0.625, "max": 0.38594666719436643, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 15.666600465774536, "min": -58.52519977092743, "max": 49.21760034561157, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.10239608147565056, "min": -0.625, "max": 0.38594666719436643, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 15.666600465774536, "min": -58.52519977092743, "max": 49.21760034561157, "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": 0.11955090509727598, "min": 0.0549288809299469, "max": 0.15605423919235667, "count": 295 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.11955090509727598, "min": 0.0549288809299469, "max": 0.15605423919235667, "count": 295 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07651706002652645, "min": 0.0008761773497099057, "max": 0.0770426332950592, "count": 295 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07651706002652645, "min": 0.0008761773497099057, "max": 0.0770426332950592, "count": 295 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07690190883974234, "min": 0.0009618056486942805, "max": 0.07727048384646575, "count": 295 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.07690190883974234, "min": 0.0009618056486942805, "max": 0.07727048384646575, "count": 295 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 2.8909994219998365e-07, "min": 2.8909994219998365e-07, "max": 0.0004970604005879202, "count": 295 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 2.8909994219998365e-07, "min": 2.8909994219998365e-07, "max": 0.0004970604005879202, "count": 295 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10005780000000003, "min": 0.10005780000000003, "max": 0.19941208000000002, "count": 295 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.10005780000000003, "min": 0.10005780000000003, "max": 0.19941208000000002, "count": 295 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 295 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 295 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676281927", "python_version": "3.10.8 (tags/v3.10.8:aaaf517, Oct 11 2022, 16:50:30) [MSC v.1933 64 bit (AMD64)]", "command_line_arguments": "C:\\_venv\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos_v1 --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+cu117", "numpy_version": "1.23.5", "end_time_seconds": "1676293444" }, "total": 11517.50440370012, "count": 1, "self": 0.30014590080827475, "children": { "run_training.setup": { "total": 0.12665479956194758, "count": 1, "self": 0.12665479956194758 }, "TrainerController.start_learning": { "total": 11517.07760299975, "count": 1, "self": 8.454678062349558, "children": { "TrainerController._reset_env": { "total": 6.790920899249613, "count": 25, "self": 6.790920899249613 }, "TrainerController.advance": { "total": 11501.488495837897, "count": 332189, "self": 8.324804423376918, "children": { "env_step": { "total": 7924.832759073004, "count": 332189, "self": 4662.1909966696985, "children": { "SubprocessEnvManager._take_step": { "total": 3257.769733860623, "count": 332189, "self": 67.06523498380557, "children": { "TorchPolicy.evaluate": { "total": 3190.7044988768175, "count": 634528, "self": 3190.7044988768175 } } }, "workers": { "total": 4.8720285426825285, "count": 332189, "self": 0.0, "children": { "worker_root": { "total": 11500.661082218867, "count": 332189, "is_parallel": true, "self": 7801.927220531274, "children": { "steps_from_proto": { "total": 0.045304300263524055, "count": 50, "is_parallel": true, "self": 0.009331699926406145, "children": { "_process_rank_one_or_two_observation": { "total": 0.03597260033711791, "count": 200, "is_parallel": true, "self": 0.03597260033711791 } } }, "UnityEnvironment.step": { "total": 3698.6885573873296, "count": 332189, "is_parallel": true, "self": 190.02568586403504, "children": { "UnityEnvironment._generate_step_input": { "total": 144.70981773221865, "count": 332189, "is_parallel": true, "self": 144.70981773221865 }, "communicator.exchange": { "total": 2766.456783823669, "count": 332189, "is_parallel": true, "self": 2766.456783823669 }, "steps_from_proto": { "total": 597.496269967407, "count": 664378, "is_parallel": true, "self": 122.68107999535277, "children": { "_process_rank_one_or_two_observation": { "total": 474.8151899720542, "count": 2657512, "is_parallel": true, "self": 474.8151899720542 } } } } } } } } } } }, "trainer_advance": { "total": 3568.330932341516, "count": 332189, "self": 65.08589063258842, "children": { "process_trajectory": { "total": 2240.8907405100763, "count": 332189, "self": 2237.5077686090954, "children": { "RLTrainer._checkpoint": { "total": 3.3829719009809196, "count": 10, "self": 3.3829719009809196 } } }, "_update_policy": { "total": 1262.3543011988513, "count": 295, "self": 116.87342757498845, "children": { "TorchPOCAOptimizer.update": { "total": 1145.4808736238629, "count": 8862, "self": 1145.4808736238629 } } } } } } }, "trainer_threads": { "total": 1.400243490934372e-06, "count": 1, "self": 1.400243490934372e-06 }, "TrainerController._save_models": { "total": 0.34350680001080036, "count": 1, "self": 0.050042600370943546, "children": { "RLTrainer._checkpoint": { "total": 0.2934641996398568, "count": 1, "self": 0.2934641996398568 } } } } } } }