Cong Lu's Projects
🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
Check out the new game server:
Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models
char* bloom filter implemented in shared memory
Submission for MAVEN: Multi-Agent Variational Exploration
An open source robotics benchmark for meta- and multi-task reinforcement learning
A collection of MuJoCo based environments.
Code to accompany the paper 'On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations'
ROBEL: Robotics Benchmarks for Learning with low-cost robots
Automatically exported from code.google.com/p/smhasher
Synthetic Experience Replay
Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations