3 papers
cs.AI2026
Decoupled Behavioral Cloning for Scalable Inductive Generalization in RL from Specifications
Vignesh Subramanian, Subhajit Roy, Suguman Bansal
Inductive generalization is a framework for reinforcement learning (RL) generalization in which inductively related task instances admit inductively related policies. Prior work ca…
cs.PL2024
Synthesizing Abstract Transformers for Reduced-Product Domains
Pankaj Kumar Kalita, Thomas Reps, Subhajit Roy
Recently, we showed how to apply program-synthesis techniques to create abstract transformers in a user-provided domain-specific language (DSL) L (i.e., ''L-transformers"). However…
cs.LG2024
Inductive Generalization in Reinforcement Learning from Specifications
Vignesh Subramanian, Rohit Kushwah, Subhajit Roy +1
We present a novel inductive generalization framework for RL from logical specifications. Many interesting tasks in RL environments have a natural inductive structure. These induct…