{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4183956384658813, "min": 1.398594617843628, "max": 1.6958080530166626, "count": 1660 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27687.08203125, "min": 15082.263671875, "max": 40202.734375, "count": 1660 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.51111111111111, "min": 38.06349206349206, "max": 81.078125, "count": 1660 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19624.0, "min": 7724.0, "max": 21236.0, "count": 1660 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1818.2583582664433, "min": 1745.2337641544154, "max": 1861.1968735340065, "count": 1660 }, "SoccerTwos.Self-play.ELO.sum": { "value": 327286.5044879598, "min": 110774.77417624679, "max": 449836.55641888897, "count": 1660 }, "SoccerTwos.Step.mean": { "value": 50239952.0, "min": 33649896.0, "max": 50239952.0, "count": 1660 }, "SoccerTwos.Step.sum": { "value": 50239952.0, "min": 33649896.0, "max": 50239952.0, "count": 1660 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0067557236179709435, "min": -0.15469954907894135, "max": 0.07358665019273758, "count": 1660 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.2092745304107666, "min": -29.23821449279785, "max": 12.918013572692871, "count": 1660 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.00687007000669837, "min": -0.15562890470027924, "max": 0.07387322932481766, "count": 1660 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.2297425270080566, "min": -29.413862228393555, "max": 13.666547775268555, "count": 1660 }, "SoccerTwos.Policy.CuriosityBaselineEstimate.mean": { "value": 0.003615199588239193, "min": 0.0031208039727061987, "max": 0.007002003025263548, "count": 1660 }, "SoccerTwos.Policy.CuriosityBaselineEstimate.sum": { "value": 0.6471207141876221, "min": 0.381656676530838, "max": 1.4521714448928833, "count": 1660 }, "SoccerTwos.Policy.CuriosityValueEstimate.mean": { "value": 0.0036184925120323896, "min": 0.0031035703141242266, "max": 0.006959179881960154, "count": 1660 }, "SoccerTwos.Policy.CuriosityValueEstimate.sum": { "value": 0.6477101445198059, "min": 0.3785913586616516, "max": 1.4337968826293945, "count": 1660 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1660 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1660 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.0617385476661128, "min": -0.42737910373887017, "max": 0.32229863209267184, "count": 1660 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -11.051200032234192, "min": -75.04779988527298, "max": 56.9405996799469, "count": 1660 }, "SoccerTwos.Policy.CuriosityReward.mean": { "value": 0.019947295109663345, "min": 0.0, "max": 0.04713458152115345, "count": 1660 }, "SoccerTwos.Policy.CuriosityReward.sum": { "value": 3.570565824629739, "min": 0.0, "max": 6.357237994438037, "count": 1660 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.0617385476661128, "min": -0.42737910373887017, "max": 0.32229863209267184, "count": 1660 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -11.051200032234192, "min": -75.04779988527298, "max": 56.9405996799469, "count": 1660 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1660 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1660 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.011817872176519207, "min": 0.010732746903910689, "max": 0.013871164493029936, "count": 80 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.011817872176519207, "min": 0.010732746903910689, "max": 0.013871164493029936, "count": 80 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.06353306834896405, "min": 0.05685146570205688, "max": 0.06636625190575918, "count": 80 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.06353306834896405, "min": 0.05685146570205688, "max": 0.06636625190575918, "count": 80 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.06495661271115144, "min": 0.05810340752204259, "max": 0.0681164162606001, "count": 80 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.06495661271115144, "min": 0.05810340752204259, "max": 0.0681164162606001, "count": 80 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00013320276226576447, "min": 0.00013320276226576447, "max": 0.00018716187761272002, "count": 80 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00013320276226576447, "min": 0.00013320276226576447, "max": 0.00018716187761272002, "count": 80 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.1444009022222222, "min": 0.1444009022222222, "max": 0.16238728000000005, "count": 80 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.1444009022222222, "min": 0.1444009022222222, "max": 0.16238728000000005, "count": 80 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.0022256050208888894, "min": 0.0022256050208888894, "max": 0.0031231252720000007, "count": 80 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.0022256050208888894, "min": 0.0022256050208888894, "max": 0.0031231252720000007, "count": 80 }, "SoccerTwos.Losses.CuriosityForwardLoss.mean": { "value": 0.03468668575088183, "min": 0.03468668575088183, "max": 0.06340160754819711, "count": 80 }, "SoccerTwos.Losses.CuriosityForwardLoss.sum": { "value": 0.03468668575088183, "min": 0.03468668575088183, "max": 0.06340160754819711, "count": 80 }, "SoccerTwos.Losses.CuriosityInverseLoss.mean": { "value": 0.9865806484222412, "min": 0.9750371980667114, "max": 1.1958354528745014, "count": 80 }, "SoccerTwos.Losses.CuriosityInverseLoss.sum": { "value": 0.9865806484222412, "min": 0.9750371980667114, "max": 1.1958354528745014, "count": 80 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680197495", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:39:03) \n[GCC 11.3.0]", "command_line_arguments": "/home/ringo/mambaforge/envs/hfrl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos5 --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1680270640" }, "total": 72525.62028098898, "count": 1, "self": 1.2511183369497303, "children": { "run_training.setup": { "total": 0.012792229012120515, "count": 1, "self": 0.012792229012120515 }, "TrainerController.start_learning": { "total": 72524.35637042302, "count": 1, "self": 31.513384588295594, "children": { "TrainerController._reset_env": { "total": 2.3360127020278014, "count": 68, "self": 2.3360127020278014 }, "TrainerController.advance": { "total": 72489.9886810527, "count": 1160286, "self": 33.68587490203208, "children": { "env_step": { "total": 25242.8757303101, "count": 1160286, "self": 20391.40072442987, "children": { "SubprocessEnvManager._take_step": { "total": 4833.0395404651645, "count": 1160286, "self": 206.1031344626972, "children": { "TorchPolicy.evaluate": { "total": 4626.936406002467, "count": 2080678, "self": 4626.936406002467 } } }, "workers": { "total": 18.435465415066574, "count": 1160286, "self": 0.0, "children": { "worker_root": { "total": 72309.51445994552, "count": 1160286, "is_parallel": true, "self": 55463.927844563994, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002130955021129921, "count": 2, "is_parallel": true, "self": 0.0004951070295646787, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016358479915652424, "count": 8, "is_parallel": true, "self": 0.0016358479915652424 } } }, "UnityEnvironment.step": { "total": 0.03356915898621082, "count": 1, "is_parallel": true, "self": 0.0009080409654416144, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006295579951256514, "count": 1, "is_parallel": true, "self": 0.0006295579951256514 }, "communicator.exchange": { "total": 0.029179003002354875, "count": 1, "is_parallel": true, "self": 0.029179003002354875 }, "steps_from_proto": { "total": 0.002852557023288682, "count": 2, "is_parallel": true, "self": 0.0005235399294178933, "children": { "_process_rank_one_or_two_observation": { "total": 0.002329017093870789, "count": 8, "is_parallel": true, "self": 0.002329017093870789 } } } } } } }, "steps_from_proto": { "total": 0.1787195928627625, "count": 134, "is_parallel": true, "self": 0.04293646372389048, "children": { "_process_rank_one_or_two_observation": { "total": 0.13578312913887203, "count": 536, "is_parallel": true, "self": 0.13578312913887203 } } }, "UnityEnvironment.step": { "total": 16845.407895788667, "count": 1160285, "is_parallel": true, "self": 1038.5947901722684, "children": { "UnityEnvironment._generate_step_input": { "total": 719.4802574055211, "count": 1160285, "is_parallel": true, "self": 719.4802574055211 }, "communicator.exchange": { "total": 11960.766660614085, "count": 1160285, "is_parallel": true, "self": 11960.766660614085 }, "steps_from_proto": { "total": 3126.5661875967926, "count": 2320570, "is_parallel": true, "self": 612.0953690481547, "children": { "_process_rank_one_or_two_observation": { "total": 2514.470818548638, "count": 9282280, "is_parallel": true, "self": 2514.470818548638 } } } } } } } } } } }, "trainer_advance": { "total": 47213.42707584056, "count": 1160286, "self": 192.3163880656939, "children": { "process_trajectory": { "total": 6999.7229574489465, "count": 1160286, "self": 6990.1382673919725, "children": { "RLTrainer._checkpoint": { "total": 9.584690056974068, "count": 33, "self": 9.584690056974068 } } }, "_update_policy": { "total": 40021.38773032592, "count": 81, "self": 6133.06635880348, "children": { "TorchPOCAOptimizer.update": { "total": 33888.32137152244, "count": 12033, "self": 33888.32137152244 } } } } } } }, "trainer_threads": { "total": 2.0560109987854958e-06, "count": 1, "self": 2.0560109987854958e-06 }, "TrainerController._save_models": { "total": 0.5182900239888113, "count": 1, "self": 0.0029413799929898232, "children": { "RLTrainer._checkpoint": { "total": 0.5153486439958215, "count": 1, "self": 0.5153486439958215 } } } } } } }