{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.403570294380188, "min": 1.403570294380188, "max": 1.4252015352249146, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70185.53125, "min": 69217.5546875, "max": 78375.484375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 77.359375, "min": 73.2893175074184, "max": 377.6466165413534, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49510.0, "min": 49179.0, "max": 50227.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999953.0, "min": 49610.0, "max": 1999953.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999953.0, "min": 49610.0, "max": 1999953.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.504476547241211, "min": 0.04939119890332222, "max": 2.5505175590515137, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1600.3604736328125, "min": 6.5196380615234375, "max": 1695.41455078125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.927538194007157, "min": 1.7326125385183277, "max": 4.088473511403441, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2509.6969059705734, "min": 228.70485508441925, "max": 2705.9666652679443, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.927538194007157, "min": 1.7326125385183277, "max": 4.088473511403441, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2509.6969059705734, "min": 228.70485508441925, "max": 2705.9666652679443, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01704751167049431, "min": 0.014002482304931618, "max": 0.01958663995998601, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05114253501148293, "min": 0.028004964609863237, "max": 0.05538411399465985, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05898604343334834, "min": 0.021394834884752828, "max": 0.06691374368965625, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.176958130300045, "min": 0.042789669769505656, "max": 0.19561518107851347, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7261487579833243e-06, "min": 3.7261487579833243e-06, "max": 0.000295340326553225, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1178446273949973e-05, "min": 1.1178446273949973e-05, "max": 0.0008440054686648498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1012420166666667, "min": 0.1012420166666667, "max": 0.198446775, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3037260500000001, "min": 0.20766925, "max": 0.5813351500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.197663166666651e-05, "min": 7.197663166666651e-05, "max": 0.0049224940725, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021592989499999955, "min": 0.00021592989499999955, "max": 0.014068623985, "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": "1728481961", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "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": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1728484504" }, "total": 2543.47891985, "count": 1, "self": 0.8771962189998703, "children": { "run_training.setup": { "total": 0.07387150799968367, "count": 1, "self": 0.07387150799968367 }, "TrainerController.start_learning": { "total": 2542.5278521230002, "count": 1, "self": 4.584194634936466, "children": { "TrainerController._reset_env": { "total": 2.414379838000059, "count": 1, "self": 2.414379838000059 }, "TrainerController.advance": { "total": 2535.3216703390635, "count": 233381, "self": 4.638598615091269, "children": { "env_step": { "total": 2003.9238194058494, "count": 233381, "self": 1584.3946228258787, "children": { "SubprocessEnvManager._take_step": { "total": 416.60693741181603, "count": 233381, "self": 15.98369779490713, "children": { "TorchPolicy.evaluate": { "total": 400.6232396169089, "count": 222926, "self": 400.6232396169089 } } }, "workers": { "total": 2.9222591681545964, "count": 233381, "self": 0.0, "children": { "worker_root": { "total": 2534.84520328072, "count": 233381, "is_parallel": true, "self": 1252.238385792547, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008970619996944151, "count": 1, "is_parallel": true, "self": 0.0002828909996424045, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006141710000520106, "count": 2, "is_parallel": true, "self": 0.0006141710000520106 } } }, "UnityEnvironment.step": { "total": 0.02942977200018504, "count": 1, "is_parallel": true, "self": 0.00038758900063839974, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019534599960024934, "count": 1, "is_parallel": true, "self": 0.00019534599960024934 }, "communicator.exchange": { "total": 0.028087040000173147, "count": 1, "is_parallel": true, "self": 0.028087040000173147 }, "steps_from_proto": { "total": 0.0007597969997732434, "count": 1, "is_parallel": true, "self": 0.0002137080000466085, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005460889997266349, "count": 2, "is_parallel": true, "self": 0.0005460889997266349 } } } } } } }, "UnityEnvironment.step": { "total": 1282.606817488173, "count": 233380, "is_parallel": true, "self": 38.350114682562435, "children": { "UnityEnvironment._generate_step_input": { "total": 83.14231282494029, "count": 233380, "is_parallel": true, "self": 83.14231282494029 }, "communicator.exchange": { "total": 1069.6676072297491, "count": 233380, "is_parallel": true, "self": 1069.6676072297491 }, "steps_from_proto": { "total": 91.4467827509211, "count": 233380, "is_parallel": true, "self": 34.222350311137234, "children": { "_process_rank_one_or_two_observation": { "total": 57.22443243978387, "count": 466760, "is_parallel": true, "self": 57.22443243978387 } } } } } } } } } } }, "trainer_advance": { "total": 526.7592523181229, "count": 233381, "self": 6.532418793189663, "children": { "process_trajectory": { "total": 173.307000407935, "count": 233381, "self": 171.80716032093414, "children": { "RLTrainer._checkpoint": { "total": 1.4998400870008481, "count": 10, "self": 1.4998400870008481 } } }, "_update_policy": { "total": 346.91983311699823, "count": 97, "self": 280.43048342400834, "children": { "TorchPPOOptimizer.update": { "total": 66.48934969298989, "count": 2910, "self": 66.48934969298989 } } } } } } }, "trainer_threads": { "total": 1.4670004020445049e-06, "count": 1, "self": 1.4670004020445049e-06 }, "TrainerController._save_models": { "total": 0.20760584399977233, "count": 1, "self": 0.0044968329993935185, "children": { "RLTrainer._checkpoint": { "total": 0.20310901100037881, "count": 1, "self": 0.20310901100037881 } } } } } } }