cs.LGNov 5, 2026

The Blindfolded Controller: Decision Model-Guided Training for Reinforcement Learning

Authors: Muhammad Ibrahim Khan, Aniket Dixit, Faizan Ahmed, James Brusey

Organizations: Coventry University, Coventry, UK

Abstract

Reinforcement learning (RL) provides a framework for continuous improvement through interaction with an environment. However, RL agents struggle against tasks that offer exploration challenges and sparse rewards, because learning efficient policies from scratch is slow and sample-inefficient. In contrast, decision models (DMs), given a description of the environment and task, can perform well in sparse-reward tasks, but, as they do not learn from reward, they are not able to improve towards the optimal solution. In this paper, we present Decision Model-Guided Training (DMGT), a technique that uses a DM with a description of the environment and task to initialise an RL policy, combining the DM's ability to act without training with RL's ability to improve from reward. Instead of exploring from scratch, the agent reaches the goal and receives reward from its first episodes, and RL then improves its policy beyond what the DM achieves. We demonstrate through experiments on seven tasks that our approach outperforms RL in all seven and DM in five. In addition, we provide comprehensive guidelines, derived from ablation studies, for describing an environment and task to a DM.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Model What Matters: Decision-Guided Selective World Modeling for Language Agents

    Oct 14, 2026Maolin Ran, Minda Chen, Di Huang +3World ModelsRL for LLM Agents

  2. Discretizing Reward Models

    Jun 19, 2026Vijay Viswanathan, Shiqi Wang, Devamanyu Hazarika +4Reward ModelingReinforcement Learning

  3. Can Jev be Your Q or Policy in Reinforcement Learning?

    Oct 8, 2026Yi Ma, Tianpei Yang, Yaodong Yang +2LLM-Guided RLSample-Efficient RL