226 citations · 1k across the 102 of their papers we have counts for
16 papers · 1 filter
Guaranteed Trust Region Optimization via Two-Phase KL Penalization
K. R. Zentner, Ujjwal Puri, Zhehui Huang +1
On-policy reinforcement learning (RL) has become a popular framework for solving sequential decision problems due to its computational efficiency and theoretical simplicity. Some o…
Conditionally Combining Robot Skills using Large Language Models
K. R. Zentner, Ryan Julian, Brian Ichter +1
This paper combines two contributions. First, we introduce an extension of the Meta-World benchmark, which we call "Language-World," which allows a large language model to operate…
Exploiting Generalization in Offline Reinforcement Learning via Unseen State Augmentations
Nirbhay Modhe, Qiaozi Gao, Ashwin Kalyan +3
Offline reinforcement learning (RL) methods strike a balance between exploration and exploitation by conservative value estimation -- penalizing values of unseen states and actions…
Generating Behaviorally Diverse Policies with Latent Diffusion Models
Shashank Hegde, Sumeet Batra, K. R. Zentner +1
Recent progress in Quality Diversity Reinforcement Learning (QD-RL) has enabled learning a collection of behaviorally diverse, high performing policies. However, these methods typi…
Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning
Sumeet Batra, Bryon Tjanaka, Matthew C. Fontaine +3
Training generally capable agents that thoroughly explore their environment and learn new and diverse skills is a long-term goal of robot learning. Quality Diversity Reinforcement…
OpenD: A Benchmark for Language-Driven Door and Drawer Opening
Yizhou Zhao, Qiaozi Gao, Liang Qiu +2
We introduce OPEND, a benchmark for learning how to use a hand to open cabinet doors or drawers in a photo-realistic and physics-reliable simulation environment driven by language…