7 papers
RL with Learnable Textual Feedback: A Bilevel Approach
Utsav Singh, Sidhaarth Sredharan, Souradip Chakraborty +1
Reinforcement learning with verifiable rewards can improve LLM reasoning, but learning remains sample-inefficient when terminal rewards are sparse. This has motivated a growing lin…
Direct Preference Optimization for Primitive-Enabled Hierarchical RL: A Bilevel Approach
Utsav Singh, Souradip Chakraborty, Wesley A. Suttle +6
Hierarchical reinforcement learning (HRL) enables agents to solve complex, long-horizon tasks by decomposing them into manageable sub-tasks. However, HRL methods face two fundament…
MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Models
Kevin Zhai, Utsav Singh, Anirudh Thatipelli +5
Diffusion models excel at generating images conditioned on text prompts, but the resulting images often do not satisfy user-specific criteria measured by scalar rewards such as Aes…
Training Fast Robot Policies with Slow Foundation Models
Utsav Singh, Pramit Bhattacharyya, Vinay P. Namboodiri +1
Continuous robotic control requires policies that execute with low latency and modest computational cost during deployment. Foundation models provide strong semantic and visual rea…
CRISP: Curriculum Inducing Primitive Informed Subgoal Prediction for Hierarchical Reinforcement Learning
Utsav Singh, Vinay P. Namboodiri
Hierarchical reinforcement learning (HRL) leverages temporal abstraction to efficiently tackle complex long-horizon tasks. However, HRL often collapses because the continual update…
PEAR: Primitive Enabled Adaptive Relabeling for Boosting Hierarchical Reinforcement Learning
Utsav Singh, Vinay P. Namboodiri
Hierarchical reinforcement learning (HRL) has the potential to solve complex long horizon tasks using temporal abstraction and increased exploration. However, hierarchical agents a…