{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.408603549003601, "min": 1.408603549003601, "max": 1.4279448986053467, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70458.3515625, "min": 68349.1328125, "max": 77882.171875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 103.18930041152264, "min": 84.04081632653062, "max": 412.9917355371901, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 50150.0, "min": 48950.0, "max": 50150.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999935.0, "min": 49760.0, "max": 1999935.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999935.0, "min": 49760.0, "max": 1999935.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.33236026763916, "min": 0.09061726927757263, "max": 2.4202773571014404, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1133.527099609375, "min": 10.874072074890137, "max": 1414.1080322265625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.591380107304687, "min": 1.853114574154218, "max": 3.915897422202132, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1745.4107321500778, "min": 222.37374889850616, "max": 2204.7125654816628, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.591380107304687, "min": 1.853114574154218, "max": 3.915897422202132, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1745.4107321500778, "min": 222.37374889850616, "max": 2204.7125654816628, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015116105638783968, "min": 0.012770614392259934, "max": 0.01972997129681365, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.045348316916351904, "min": 0.02554122878451987, "max": 0.05409161865633602, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.050459805420703364, "min": 0.022937269943455855, "max": 0.05795225134740273, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1513794162621101, "min": 0.04587453988691171, "max": 0.16643543168902397, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4329988556999933e-06, "min": 3.4329988556999933e-06, "max": 0.00029531647656117497, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.029899656709998e-05, "min": 1.029899656709998e-05, "max": 0.00084425926858025, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10114429999999998, "min": 0.10114429999999998, "max": 0.19843882499999999, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30343289999999995, "min": 0.20743125, "max": 0.5814197499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.710056999999991e-05, "min": 6.710056999999991e-05, "max": 0.004922097367500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020130170999999974, "min": 0.00020130170999999974, "max": 0.014072845525000002, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1740956985", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740959821" }, "total": 2835.86347975, "count": 1, "self": 0.6421837260004395, "children": { "run_training.setup": { "total": 0.02539389499997924, "count": 1, "self": 0.02539389499997924 }, "TrainerController.start_learning": { "total": 2835.1959021289995, "count": 1, "self": 5.114048592044128, "children": { "TrainerController._reset_env": { "total": 3.4029496920002202, "count": 1, "self": 3.4029496920002202 }, "TrainerController.advance": { "total": 2826.4781920239557, "count": 231879, "self": 5.257052468951315, "children": { "env_step": { "total": 2290.384276889981, "count": 231879, "self": 1798.0861511672492, "children": { "SubprocessEnvManager._take_step": { "total": 489.06177918492085, "count": 231879, "self": 18.24213778803096, "children": { "TorchPolicy.evaluate": { "total": 470.8196413968899, "count": 223049, "self": 470.8196413968899 } } }, "workers": { "total": 3.236346537810732, "count": 231879, "self": 0.0, "children": { "worker_root": { "total": 2826.5774581080877, "count": 231879, "is_parallel": true, "self": 1363.6340024350156, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001212507999753143, "count": 1, "is_parallel": true, "self": 0.00031102999992072, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009014779998324229, "count": 2, "is_parallel": true, "self": 0.0009014779998324229 } } }, "UnityEnvironment.step": { "total": 0.03683169599980829, "count": 1, "is_parallel": true, "self": 0.0003896779994647659, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002223980000053416, "count": 1, "is_parallel": true, "self": 0.0002223980000053416 }, "communicator.exchange": { "total": 0.03532766700027423, "count": 1, "is_parallel": true, "self": 0.03532766700027423 }, "steps_from_proto": { "total": 0.0008919530000639497, "count": 1, "is_parallel": true, "self": 0.000260570000136795, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006313829999271547, "count": 2, "is_parallel": true, "self": 0.0006313829999271547 } } } } } } }, "UnityEnvironment.step": { "total": 1462.943455673072, "count": 231878, "is_parallel": true, "self": 42.13152798964575, "children": { "UnityEnvironment._generate_step_input": { "total": 95.82859288314603, "count": 231878, "is_parallel": true, "self": 95.82859288314603 }, "communicator.exchange": { "total": 1224.14892006917, "count": 231878, "is_parallel": true, "self": 1224.14892006917 }, "steps_from_proto": { "total": 100.83441473111043, "count": 231878, "is_parallel": true, "self": 38.26580346120181, "children": { "_process_rank_one_or_two_observation": { "total": 62.568611269908615, "count": 463756, "is_parallel": true, "self": 62.568611269908615 } } } } } } } } } } }, "trainer_advance": { "total": 530.8368626650235, "count": 231879, "self": 7.633561938914681, "children": { "process_trajectory": { "total": 188.35235342810756, "count": 231879, "self": 186.88816169010488, "children": { "RLTrainer._checkpoint": { "total": 1.4641917380026825, "count": 10, "self": 1.4641917380026825 } } }, "_update_policy": { "total": 334.8509472980013, "count": 97, "self": 265.7127434989993, "children": { "TorchPPOOptimizer.update": { "total": 69.13820379900199, "count": 2910, "self": 69.13820379900199 } } } } } } }, "trainer_threads": { "total": 1.2040000001434237e-06, "count": 1, "self": 1.2040000001434237e-06 }, "TrainerController._save_models": { "total": 0.20071061699945858, "count": 1, "self": 0.003263606999098556, "children": { "RLTrainer._checkpoint": { "total": 0.19744701000036002, "count": 1, "self": 0.19744701000036002 } } } } } } }