{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.7592885494232178, "min": 2.7592885494232178, "max": 2.867496967315674, "count": 2 }, "SnowballTarget.Policy.Entropy.sum": { "value": 28439.98828125, "min": 28439.98828125, "max": 29397.580078125, "count": 2 }, "SnowballTarget.Step.mean": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Step.sum": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 1.4529480934143066, "min": 0.3814451992511749, "max": 1.4529480934143066, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 297.8543701171875, "min": 74.0003662109375, "max": 297.8543701171875, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06775400159125959, "min": 0.06775400159125959, "max": 0.06921998382018929, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.33877000795629797, "min": 0.27687993528075716, "max": 0.33877000795629797, "count": 2 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2051699895893826, "min": 0.12378139048472375, "max": 0.2051699895893826, "count": 2 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.025849947946913, "min": 0.495125561938895, "max": 1.025849947946913, "count": 2 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.032007656e-05, "min": 7.032007656e-05, "max": 0.00021882002706000002, "count": 2 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0003516003828, "min": 0.0003516003828, "max": 0.0008752801082400001, "count": 2 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.12344, "min": 0.12344, "max": 0.17294, "count": 2 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.6172, "min": 0.6172, "max": 0.69176, "count": 2 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0011796560000000005, "min": 0.0011796560000000005, "max": 0.0036497060000000004, "count": 2 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.005898280000000002, "min": 0.005898280000000002, "max": 0.014598824000000002, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 6.5636363636363635, "min": 3.7045454545454546, "max": 6.5636363636363635, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 361.0, "min": 163.0, "max": 361.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 6.5636363636363635, "min": 3.7045454545454546, "max": 6.5636363636363635, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 361.0, "min": 163.0, "max": 361.0, "count": 2 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686002220", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1686002294" }, "total": 73.902339042, "count": 1, "self": 0.7763819560000229, "children": { "run_training.setup": { "total": 0.037074524999979985, "count": 1, "self": 0.037074524999979985 }, "TrainerController.start_learning": { "total": 73.08888256099999, "count": 1, "self": 0.10041775599813718, "children": { "TrainerController._reset_env": { "total": 3.5596899549999534, "count": 1, "self": 3.5596899549999534 }, "TrainerController.advance": { "total": 69.20276343600199, "count": 1889, "self": 0.024677614003167037, "children": { "env_step": { "total": 69.17808582199882, "count": 1889, "self": 56.00599159299668, "children": { "SubprocessEnvManager._take_step": { "total": 13.147290013002248, "count": 1889, "self": 0.15501957900289653, "children": { "TorchPolicy.evaluate": { "total": 12.992270433999352, "count": 1889, "self": 12.992270433999352 } } }, "workers": { "total": 0.02480421599989313, "count": 1889, "self": 0.0, "children": { "worker_root": { "total": 72.72249690699982, "count": 1889, "is_parallel": true, "self": 49.205026782000346, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001891798999963612, "count": 1, "is_parallel": true, "self": 0.0005712810000204627, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013205179999431493, "count": 10, "is_parallel": true, "self": 0.0013205179999431493 } } }, "UnityEnvironment.step": { "total": 0.037282495999988896, "count": 1, "is_parallel": true, "self": 0.0006252550001590862, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003013219999274952, "count": 1, "is_parallel": true, "self": 0.0003013219999274952 }, "communicator.exchange": { "total": 0.03407865799999854, "count": 1, "is_parallel": true, "self": 0.03407865799999854 }, "steps_from_proto": { "total": 0.002277260999903774, "count": 1, "is_parallel": true, "self": 0.0005112659999895186, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017659949999142555, "count": 10, "is_parallel": true, "self": 0.0017659949999142555 } } } } } } }, "UnityEnvironment.step": { "total": 23.517470124999477, "count": 1888, "is_parallel": true, "self": 0.9725954869967381, "children": { "UnityEnvironment._generate_step_input": { "total": 0.5375511420010071, "count": 1888, "is_parallel": true, "self": 0.5375511420010071 }, "communicator.exchange": { "total": 18.704511142001707, "count": 1888, "is_parallel": true, "self": 18.704511142001707 }, "steps_from_proto": { "total": 3.302812354000025, "count": 1888, "is_parallel": true, "self": 0.6177779469970801, "children": { "_process_rank_one_or_two_observation": { "total": 2.685034407002945, "count": 18880, "is_parallel": true, "self": 2.685034407002945 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00026957499994750833, "count": 1, "self": 0.00026957499994750833, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 68.90451112098981, "count": 41650, "is_parallel": true, "self": 0.9375681819861938, "children": { "process_trajectory": { "total": 25.398075414003756, "count": 41650, "is_parallel": true, "self": 24.1889189790038, "children": { "RLTrainer._checkpoint": { "total": 1.2091564349999544, "count": 4, "is_parallel": true, "self": 1.2091564349999544 } } }, "_update_policy": { "total": 42.56886752499986, "count": 9, "is_parallel": true, "self": 18.569939660002774, "children": { "TorchPPOOptimizer.update": { "total": 23.998927864997086, "count": 1520, "is_parallel": true, "self": 23.998927864997086 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2257418389999657, "count": 1, "self": 0.0017498859999705019, "children": { "RLTrainer._checkpoint": { "total": 0.2239919529999952, "count": 1, "self": 0.2239919529999952 } } } } } } }