{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.073544979095459, "min": 2.073544979095459, "max": 3.295722723007202, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40011.125, "min": 17774.3203125, "max": 123155.9765625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 47.407766990291265, "min": 42.71052631578947, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19532.0, "min": 13104.0, "max": 27908.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1530.5214059668333, "min": 1197.338280397431, "max": 1536.2752351188674, "count": 455 }, "SoccerTwos.Self-play.ELO.sum": { "value": 315287.40962916764, "min": 2395.6406482225407, "max": 338069.3745882581, "count": 455 }, "SoccerTwos.Step.mean": { "value": 4999941.0, "min": 9972.0, "max": 4999941.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999941.0, "min": 9972.0, "max": 4999941.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.044154439121484756, "min": -0.11047197878360748, "max": 0.18677304685115814, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 9.139968872070312, "min": -20.76873207092285, "max": 31.017196655273438, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.04715830460190773, "min": -0.09901896119117737, "max": 0.17889966070652008, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 9.76176929473877, "min": -18.71782875061035, "max": 31.339508056640625, "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": -0.15214299464571304, "min": -0.6037285732371467, "max": 0.461738462631519, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -31.493599891662598, "min": -52.06119978427887, "max": 56.96719992160797, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.15214299464571304, "min": -0.6037285732371467, "max": 0.461738462631519, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -31.493599891662598, "min": -52.06119978427887, "max": 56.96719992160797, "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": 0.019907069373099755, "min": 0.010999497660668567, "max": 0.022822708737415574, "count": 237 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019907069373099755, "min": 0.010999497660668567, "max": 0.022822708737415574, "count": 237 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09903378958503405, "min": 1.4826956430624706e-06, "max": 0.10611215382814407, "count": 237 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09903378958503405, "min": 1.4826956430624706e-06, "max": 0.10611215382814407, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10096097265680631, "min": 2.2768891881241872e-06, "max": 0.10855208511153856, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10096097265680631, "min": 2.2768891881241872e-06, "max": 0.10855208511153856, "count": 237 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 237 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 237 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 237 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 237 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 237 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 237 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1740015763", "python_version": "3.10.12 (main, Jul 5 2023, 15:34:07) [Clang 14.0.6 ]", "command_line_arguments": "/Users/christopherried/miniconda/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2", "numpy_version": "1.23.5", "end_time_seconds": "1740034466" }, "total": 18703.406426667, "count": 1, "self": 0.5488614579990099, "children": { "run_training.setup": { "total": 0.24192266699901666, "count": 1, "self": 0.24192266699901666 }, "TrainerController.start_learning": { "total": 18702.615642542, "count": 1, "self": 3.039812376129703, "children": { "TrainerController._reset_env": { "total": 8.344496417003029, "count": 25, "self": 8.344496417003029 }, "TrainerController.advance": { "total": 18691.150191248867, "count": 335723, "self": 3.059594879101496, "children": { "env_step": { "total": 14839.703953800014, "count": 335723, "self": 14373.612442651409, "children": { "SubprocessEnvManager._take_step": { "total": 463.8422457955021, "count": 335723, "self": 15.268253896187161, "children": { "TorchPolicy.evaluate": { "total": 448.57399189931493, "count": 637778, "self": 448.57399189931493 } } }, "workers": { "total": 2.249265353102601, "count": 335723, "self": 0.0, "children": { "worker_root": { "total": 18691.782607329926, "count": 335723, "is_parallel": true, "self": 4684.161519784264, "children": { "steps_from_proto": { "total": 0.03717392300859501, "count": 50, "is_parallel": true, "self": 0.004857292031374527, "children": { "_process_rank_one_or_two_observation": { "total": 0.032316630977220484, "count": 200, "is_parallel": true, "self": 0.032316630977220484 } } }, "UnityEnvironment.step": { "total": 14007.583913622653, "count": 335723, "is_parallel": true, "self": 37.47121835343751, "children": { "UnityEnvironment._generate_step_input": { "total": 247.11113200856562, "count": 335723, "is_parallel": true, "self": 247.11113200856562 }, "communicator.exchange": { "total": 13255.785749119525, "count": 335723, "is_parallel": true, "self": 13255.785749119525 }, "steps_from_proto": { "total": 467.2158141411255, "count": 671446, "is_parallel": true, "self": 54.13088047097335, "children": { "_process_rank_one_or_two_observation": { "total": 413.08493367015217, "count": 2685784, "is_parallel": true, "self": 413.08493367015217 } } } } } } } } } } }, "trainer_advance": { "total": 3848.3866425697506, "count": 335723, "self": 26.067895859150667, "children": { "process_trajectory": { "total": 583.286690374598, "count": 335723, "self": 582.4373964575916, "children": { "RLTrainer._checkpoint": { "total": 0.8492939170064346, "count": 10, "self": 0.8492939170064346 } } }, "_update_policy": { "total": 3239.032056336002, "count": 237, "self": 321.79181848685766, "children": { "TorchPOCAOptimizer.update": { "total": 2917.2402378491443, "count": 7110, "self": 2917.2402378491443 } } } } } } }, "trainer_threads": { "total": 5.000001692678779e-07, "count": 1, "self": 5.000001692678779e-07 }, "TrainerController._save_models": { "total": 0.08114199999909033, "count": 1, "self": 0.0006171659988467582, "children": { "RLTrainer._checkpoint": { "total": 0.08052483400024357, "count": 1, "self": 0.08052483400024357 } } } } } } }