7 papers
LexiSafe: Offline Safe Reinforcement Learning with Lexicographic Safety-Reward Hierarchy
Hsin-Jung Yang, Zhanhong Jiang, Prajwal Koirala +3
Offline safe reinforcement learning (RL) is increasingly important for cyber-physical systems (CPS), where safety violations during training are unacceptable and only pre-collected…
Flow-Based Single-Step Completion for Efficient and Expressive Policy Learning
Prajwal Koirala, Cody Fleming
Generative models such as diffusion and flow-matching offer expressive policies for offline reinforcement learning (RL) by capturing rich, multimodal action distributions, but thei…
LCLA: Language-Conditioned Latent Alignment for Vision-Language Navigation
Nitesh Subedi, Adam Haroon, Samuel Tetteh +3
We propose LCLA (Language-Conditioned Latent Alignment), a framework for vision-language navigation that learns modular perception-action interfaces by aligning sensory observation…
Can Pretrained Vision-Language Embeddings Alone Guide Robot Navigation?
Nitesh Subedi, Adam Haroon, Shreyan Ganguly +4
Foundation models have revolutionized robotics by providing rich semantic representations without task-specific training. While many approaches integrate pretrained vision-language…
Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning
Prajwal Koirala, Zhanhong Jiang, Soumik Sarkar +1
In safe offline reinforcement learning (RL), the objective is to develop a policy that maximizes cumulative rewards while strictly adhering to safety constraints, utilizing only of…
FAWAC: Feasibility Informed Advantage Weighted Regression for Persistent Safety in Offline Reinforcement Learning
Prajwal Koirala, Zhanhong Jiang, Soumik Sarkar +1
Safe offline reinforcement learning aims to learn policies that maximize cumulative rewards while adhering to safety constraints, using only offline data for training. A key challe…