Home
last modified time | relevance | path

Searched defs:reward (Results 1 – 8 of 8) sorted by relevance

/aosp_15_r20/external/pytorch/test/cpp/api/
H A Dintegration.cpp35 double reward; member in CartPole
231 auto reward = env.getReward(); in TEST_F() local
/aosp_15_r20/external/pytorch/torch/testing/_internal/distributed/rpc/examples/
H A Dreinforcement_learning_rpc_test.py160 def report_reward(self, ob_id, reward): argument
/aosp_15_r20/external/pytorch/torch/
H A D_tensor.py694 def reinforce(self, reward): argument
/aosp_15_r20/prebuilts/misc/common/robolectric/android-all/
HDandroid-all-13-robolectric-9030017.jarMETA-INF/ META-INF/MANIFEST.MF AndroidManifest.xml CompanionAppsPermissions$AppPermissions.class ...
HDandroid-all-14-robolectric-10818077.jarMETA-INF/ META-INF/MANIFEST.MF META-INF/frameworks__base__services__permission__android_common__services.permission. ...
/aosp_15_r20/external/executorch/examples/mediatek/models/llm_models/weights/Llama-3.2-1B-Instruct/
H A Dtokenizer.json52519 "reward": 50107, number
/aosp_15_r20/external/executorch/examples/mediatek/models/llm_models/weights/Llama-3.2-3B-Instruct/
H A Dtokenizer.json52519 "reward": 50107, number
/aosp_15_r20/external/executorch/examples/mediatek/models/llm_models/weights/llama3-8B-instruct/
H A Dtokenizer.json52460 "reward": 50107, number