{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9567107558250427, "min": 0.9567107558250427, "max": 2.8591859340667725, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9145.1982421875, "min": 9145.1982421875, "max": 29375.275390625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.168607711791992, "min": 0.3612288236618042, "max": 13.168607711791992, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2567.87841796875, "min": 70.0783920288086, "max": 2649.701904296875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06996826207143705, "min": 0.061018904271983115, "max": 0.07278570672828139, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2798730482857482, "min": 0.24407561708793246, "max": 0.3639285336414069, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18969077120224637, "min": 0.1436661745891815, "max": 0.3070191359695266, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7587630848089855, "min": 0.574664698356726, "max": 1.5337878158863854, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.227272727272727, "min": 3.977272727272727, "max": 26.227272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1154.0, "min": 175.0, "max": 1402.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.227272727272727, "min": 3.977272727272727, "max": 26.227272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1154.0, "min": 175.0, "max": 1402.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1695620098", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "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": "1695620598" }, "total": 500.292703136, "count": 1, "self": 0.4349725409999792, "children": { "run_training.setup": { "total": 0.04197666099997832, "count": 1, "self": 0.04197666099997832 }, "TrainerController.start_learning": { "total": 499.81575393400004, "count": 1, "self": 0.5815789840060575, "children": { "TrainerController._reset_env": { "total": 4.049565763999965, "count": 1, "self": 4.049565763999965 }, "TrainerController.advance": { "total": 495.02843238199404, "count": 18202, "self": 0.30462081599057456, "children": { "env_step": { "total": 494.72381156600346, "count": 18202, "self": 358.4172429289986, "children": { "SubprocessEnvManager._take_step": { "total": 135.9948383330099, "count": 18202, "self": 1.843538510007761, "children": { "TorchPolicy.evaluate": { "total": 134.15129982300215, "count": 18202, "self": 134.15129982300215 } } }, "workers": { "total": 0.3117303039949775, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 498.1728219480003, "count": 18202, "is_parallel": true, "self": 236.18851128199975, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005362017999971158, "count": 1, "is_parallel": true, "self": 0.0039055590000884877, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014564589998826705, "count": 10, "is_parallel": true, "self": 0.0014564589998826705 } } }, "UnityEnvironment.step": { "total": 0.05101393099999996, "count": 1, "is_parallel": true, "self": 0.00042347499993411475, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003734290000352303, "count": 1, "is_parallel": true, "self": 0.0003734290000352303 }, "communicator.exchange": { "total": 0.04716167700001961, "count": 1, "is_parallel": true, "self": 0.04716167700001961 }, "steps_from_proto": { "total": 0.0030553500000110034, "count": 1, "is_parallel": true, "self": 0.0003618399999822941, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026935100000287093, "count": 10, "is_parallel": true, "self": 0.0026935100000287093 } } } } } } }, "UnityEnvironment.step": { "total": 261.98431066600057, "count": 18201, "is_parallel": true, "self": 11.115710800007832, "children": { "UnityEnvironment._generate_step_input": { "total": 5.736075435001396, "count": 18201, "is_parallel": true, "self": 5.736075435001396 }, "communicator.exchange": { "total": 205.58264137999424, "count": 18201, "is_parallel": true, "self": 205.58264137999424 }, "steps_from_proto": { "total": 39.549883050997096, "count": 18201, "is_parallel": true, "self": 7.354352425985553, "children": { "_process_rank_one_or_two_observation": { "total": 32.19553062501154, "count": 182010, "is_parallel": true, "self": 32.19553062501154 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013417399998161272, "count": 1, "self": 0.00013417399998161272, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 491.12429948398454, "count": 458707, "is_parallel": true, "self": 10.843918150947673, "children": { "process_trajectory": { "total": 269.21722374503724, "count": 458707, "is_parallel": true, "self": 268.28204372803714, "children": { "RLTrainer._checkpoint": { "total": 0.935180017000107, "count": 4, "is_parallel": true, "self": 0.935180017000107 } } }, "_update_policy": { "total": 211.06315758799963, "count": 90, "is_parallel": true, "self": 84.4435460110077, "children": { "TorchPPOOptimizer.update": { "total": 126.61961157699193, "count": 4587, "is_parallel": true, "self": 126.61961157699193 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15604263000000174, "count": 1, "self": 0.001242456999989372, "children": { "RLTrainer._checkpoint": { "total": 0.15480017300001236, "count": 1, "self": 0.15480017300001236 } } } } } } }