{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.686201810836792, "min": 1.61666738986969, "max": 3.295747995376587, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34533.4140625, "min": 22796.37109375, "max": 123212.875, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 52.197916666666664, "min": 35.23913043478261, "max": 999.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20044.0, "min": 12536.0, "max": 29880.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1534.132495824966, "min": 1186.935243241882, "max": 1543.1639635325316, "count": 967 }, "SoccerTwos.Self-play.ELO.sum": { "value": 294553.4391983935, "min": 2376.702071045951, "max": 402419.61825872667, "count": 967 }, "SoccerTwos.Step.mean": { "value": 9999942.0, "min": 9958.0, "max": 9999942.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 9999942.0, "min": 9958.0, "max": 9999942.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.019355392083525658, "min": -0.1350097954273224, "max": 0.16036485135555267, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.6968798637390137, "min": -31.9973201751709, "max": 30.285329818725586, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.020045451819896698, "min": -0.1290610134601593, "max": 0.15804734826087952, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.828681468963623, "min": -30.587461471557617, "max": 32.160972595214844, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.008518322288053822, "min": -0.6666666666666666, "max": 0.4179343758150935, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 1.62699955701828, "min": -59.665400087833405, "max": 63.84999996423721, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.008518322288053822, "min": -0.6666666666666666, "max": 0.4179343758150935, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 1.62699955701828, "min": -59.665400087833405, "max": 63.84999996423721, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013515898309803258, "min": 0.010003222804516553, "max": 0.025158150463054578, "count": 481 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013515898309803258, "min": 0.010003222804516553, "max": 0.025158150463054578, "count": 481 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10454308514793714, "min": 2.23480628468072e-06, "max": 0.13289930646618206, "count": 481 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10454308514793714, "min": 2.23480628468072e-06, "max": 0.13289930646618206, "count": 481 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1071222648024559, "min": 2.4463010580196474e-06, "max": 0.13598620593547822, "count": 481 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1071222648024559, "min": 2.4463010580196474e-06, "max": 0.13598620593547822, "count": 481 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 481 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 481 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 481 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 481 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 481 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 481 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686264110", "python_version": "3.9.16 (main, Mar 8 2023, 04:29:44) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/sergemarquie/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1686304124" }, "total": 40013.840428498, "count": 1, "self": 1.8831873169983737, "children": { "run_training.setup": { "total": 0.026542757000000083, "count": 1, "self": 0.026542757000000083 }, "TrainerController.start_learning": { "total": 40011.930698424, "count": 1, "self": 12.18690906586562, "children": { "TrainerController._reset_env": { "total": 2.7327252130034845, "count": 50, "self": 2.7327252130034845 }, "TrainerController.advance": { "total": 39996.86503493713, "count": 689146, "self": 11.745819926363765, "children": { "env_step": { "total": 9324.912220239707, "count": 689146, "self": 7817.0611804467635, "children": { "SubprocessEnvManager._take_step": { "total": 1500.466621158855, "count": 689146, "self": 61.536327906459746, "children": { "TorchPolicy.evaluate": { "total": 1438.9302932523954, "count": 1260920, "self": 1438.9302932523954 } } }, "workers": { "total": 7.384418634087954, "count": 689146, "self": 0.0, "children": { "worker_root": { "total": 39990.46302413166, "count": 689146, "is_parallel": true, "self": 33527.17045237354, "children": { "steps_from_proto": { "total": 0.0871986750357403, "count": 100, "is_parallel": true, "self": 0.01806766206580135, "children": { "_process_rank_one_or_two_observation": { "total": 0.06913101296993895, "count": 400, "is_parallel": true, "self": 0.06913101296993895 } } }, "UnityEnvironment.step": { "total": 6463.20537308309, "count": 689146, "is_parallel": true, "self": 317.29488031598976, "children": { "UnityEnvironment._generate_step_input": { "total": 189.99315053217506, "count": 689146, "is_parallel": true, "self": 189.99315053217506 }, "communicator.exchange": { "total": 5019.913023913562, "count": 689146, "is_parallel": true, "self": 5019.913023913562 }, "steps_from_proto": { "total": 936.0043183213637, "count": 1378292, "is_parallel": true, "self": 194.90452679758812, "children": { "_process_rank_one_or_two_observation": { "total": 741.0997915237756, "count": 5513168, "is_parallel": true, "self": 741.0997915237756 } } } } } } } } } } }, "trainer_advance": { "total": 30660.20699477106, "count": 689146, "self": 83.51113152349353, "children": { "process_trajectory": { "total": 3099.430254322563, "count": 689146, "self": 3096.2962366945567, "children": { "RLTrainer._checkpoint": { "total": 3.1340176280064043, "count": 20, "self": 3.1340176280064043 } } }, "_update_policy": { "total": 27477.265608925, "count": 481, "self": 1215.5197644981672, "children": { "TorchPOCAOptimizer.update": { "total": 26261.745844426834, "count": 14430, "self": 26261.745844426834 } } } } } } }, "trainer_threads": { "total": 1.047999830916524e-06, "count": 1, "self": 1.047999830916524e-06 }, "TrainerController._save_models": { "total": 0.14602816000115126, "count": 1, "self": 0.0058231729999533854, "children": { "RLTrainer._checkpoint": { "total": 0.14020498700119788, "count": 1, "self": 0.14020498700119788 } } } } } } }