hengyuan-hu

Pinned Repositories

minirts
We release dataset collected for our research, code that implement neural network models described in the paper, and scripts to reproduce all of our results, and visualization tool for visualize dataset.
Language:C++159 11 529
off-belief-learning
Implementation of the Off Belief Learning algorithm.
Language:Python40 9 137
a2c
Language:Python10 3 21
bottom-up-attention-vqa
An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge.
Language:Python746 34 47181
dem
Building deep energy models
Language:Python6 3 02
ibrl
Language:Python8 1 00
instruct-rl
Language:Python71
jax-vs-pytorch
Language:Python8 1 00
monometis
Language:Python5 1 07
rainbow
A PyTorch implementation of Rainbow DQN agent
Language:Python163 9 323

hengyuan-hu's Repositories

hengyuan-hu/bottom-up-attention-vqa
An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge.
Language:Python746 34 47181
hengyuan-hu/rainbow
A PyTorch implementation of Rainbow DQN agent
Language:Python163 9 323
hengyuan-hu/a2c
Language:Python10 3 21
hengyuan-hu/ibrl
Language:Python8 1 00
hengyuan-hu/jax-vs-pytorch
Language:Python8 1 00
hengyuan-hu/instruct-rl
Language:Python71
hengyuan-hu/dem
Building deep energy models
Language:Python6 3 02
hengyuan-hu/monometis
Language:Python5 1 07
hengyuan-hu/nogil-pybind
Language:C++4 1 01
hengyuan-hu/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).
Language:Python3 3 00
hengyuan-hu/hanabi-learning-environment
hanabi_learning_environment is a research platform for Hanabi experiments.
Language:Python1 0 03
hengyuan-hu/open_spiel
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
Language:C++1 0 0
hengyuan-hu/optim-weight-norm
Language:Python1 2 01
hengyuan-hu/vqa
Language:Python1 4 0
hengyuan-hu/dqn-hw
Language:Python0 3 00
hengyuan-hu/cs236project
Language:Python
hengyuan-hu/custom-keras
Language:Python1 0
hengyuan-hu/dm_env_rpc
A networking protocol for agent-environment communication
Language:Python0 0
hengyuan-hu/emacs-dot
Language:Emacs Lisp1 0
hengyuan-hu/gadem
Language:Python2 0
hengyuan-hu/hanabi-live
A web server that allows people to play Hanabi, a cooperative card game of logic and reasoning.
Language:TypeScript0 0
hengyuan-hu/hanabi-live-bot
An example bot for the Hanabi Live website written in Python
Language:Python0 0
hengyuan-hu/hengyuan-hu.github.io
Language:HTML1 0
hengyuan-hu/ibrl-web
Website for Imitation Bootstrapped Reinforcement Learning
Language:HTML1 0
hengyuan-hu/LLaVA
Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.
Language:Python0 0
hengyuan-hu/minimalm
Language:Ruby1 0
hengyuan-hu/net-trim
Language:Python1 0
hengyuan-hu/nogil-hanabi
Language:C++
hengyuan-hu/pybind11
Seamless operability between C++11 and Python
Language:C++0 0
hengyuan-hu/robot-lightning
Robot Controllers for Research Lightning
Language:Python