Note - this may be different from CUDA device ID, and does not follow PyTorch-like device syntax. graphics_device_id=GRAPHICS_DEVICE_ID - Which Vulkan graphics device ID to use for rendering.Defaults to cuda:0, and also follows PyTorch-like device syntax. rl_device=RL_DEVICE - Which device / ID to use for the RL algorithm.Set to cuda:0 (default) to use GPU and to cpu for CPU.
sim_device=SIM_DEVICE_TYPE - Device used for physics simulation.
seed=SEED - sets a seed value for randomizations, and overrides the default seed set up in the task config. num_envs=NUM_ENVS - selects the number of environments to use (overriding the default number of environments set in the task config). Will automatically default to the correct config for the environment (ie. train=TRAIN - selects which training config to use. Any of AllegroHand, AllegroHandDextremeADR, AllegroHandDextremeManualDR, AllegroKukaLSTM, AllegroKukaTwoArmsLSTM, Ant, Anymal, AnymalTerrain, BallBalance, Cartpole, FrankaCabinet, Humanoid, Ingenuity Quadcopter, ShadowHand, ShadowHandOpenAI_FF, ShadowHandOpenAI_LSTM, and Trifinger (these correspond to the config for each environment in the folder isaacgymenvs/config/task) task=TASK - selects which task to use. Key arguments to the train.py script are: Note that this has someĭifferences from previous incarnations in older versions of Isaac Gym. For example,Ĭheckpoint="./runs/Ant/nn/last_Antep\=501rew\.pth" Configuration and command line arguments You will need to escape them and put quotes around the string. Note that If there are special characters such as [ or = in the checkpoint names, Python train.py task=Ant checkpoint=runs/Ant/nn/Ant.pth test=True num_envs=64
0 kommentar(er)
