42 citations · 89 across the 6 of their papers we have counts for
6 papers
Lyapunov Barrier Policy Optimization
Harshit Sikchi, Wenxuan Zhou, David Held
Deploying Reinforcement Learning (RL) agents in the real-world require that the agents satisfy safety constraints. Current RL agents explore the environment without considering the…
PLAS: Latent Action Space for Offline Reinforcement Learning
Wenxuan Zhou, Sujay Bajracharya, David Held
The goal of offline reinforcement learning is to learn a policy from a fixed dataset, without further interactions with the environment. This setting will be an increasingly more i…
Learning Off-Policy with Online Planning
Harshit Sikchi, Wenxuan Zhou, David Held
Reinforcement learning (RL) in low-data and risk-sensitive domains requires performant and flexible deployment policies that can readily incorporate constraints during deployment.…
Improving BERT Fine-tuning with Embedding Normalization
Wenxuan Zhou, Junyi Du, Xiang Ren
Large pre-trained sentence encoders like BERT start a new chapter in natural language processing. A common practice to apply pre-trained BERT to sequence classification tasks (e.g.…
Environment Probing Interaction Policies
Wenxuan Zhou, Lerrel Pinto, Abhinav Gupta
A key challenge in reinforcement learning (RL) is environment generalization: a policy trained to solve a task in one environment often fails to solve the same task in a slightly d…
SWEET: Serving the Web by Exploiting Email Tunnels
Amir Houmansadr, Wenxuan Zhou, Matthew Caesar +1
Open communication over the Internet poses a serious threat to countries with repressive regimes, leading them to develop and deploy censorship mechanisms within their networks. Un…