Hengyuan Hu's repositories
bottom-up-attention-vqa
An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge.
pytorch-a2c-ppo-acktr
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO) and Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR).
hanabi-learning-environment
hanabi_learning_environment is a research platform for Hanabi experiments.
open_spiel
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
dm_env_rpc
A networking protocol for agent-environment communication
hanabi-live
A web server that allows people to play Hanabi, a cooperative card game of logic and reasoning.
hanabi-live-bot
An example bot for the Hanabi Live website written in Python
LLaVA
Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.
pybind11
Seamless operability between C++11 and Python
robot-lightning
Robot Controllers for Research Lightning