Yanlai's repositories
continual-ddpm
Continual Learning for Diffusion Models
open_spiel
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
BridgeGPT
Using GPT-4 to play the game of bridge.
cog-1
[CoRL 2020] COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning
d4rl
A benchmark for offline reinforcement learning.
DDPMs-Pytorch
Implementation of various DDPM papers to understand how they work
deep_bisim4control
Learning Invariant Representations for Reinforcement Learning without Reconstruction
homework_fall2020
Assignments for Berkeley CS 285: Deep Reinforcement Learning (Fall 2020)
llm-memory
Memory experiments with LLMs
mae
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
mrcl
Code for the NeurIPS19 paper "Meta-Learning Representations for Continual Learning"
never-give-up
PyTorch implementation of Never Give Up: Learning Directed Exploration Strategies
proto
Proto-RL: Reinforcement Learning with Prototypical Representations
reward-learning-rl
[RSS 2019] End-to-End Robotic Reinforcement Learning without Reward Engineering
stable-baselines3
PyTorch version of Stable Baselines, improved implementations of reinforcement learning algorithms.
train-procgen
CS 182 Final Project: Improving Generalization of Deep Reinforcement Learning
vds
Code for Automatic Curriculum Learning through Value Disagreement
WokePay
CalHacks 5.0