Subhajit Roy
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes DIBS, a decoupled behavioral cloning approach that stabilizes inductive generalization in RL by separating task-specific policy learning from the evolution function, leading to improved generalization and training stability.
The paper proposes DIBS, a decoupled behavioral cloning approach that stabilizes inductive generalization in RL by separating task-specific policy learning from the evolution function, leading to improved generalization and training stability.
Papers
Decoupled Behavioral Cloning for Scalable Inductive Generalization in RL from Specifications
The paper proposes DIBS, a decoupled behavioral cloning approach that stabilizes inductive generalization in RL by separating task-specific policy learning from the evolution function, leading to impr…