This is the pre-proceedings for the RLC 2026. You may expect minor changes.
Reinforcement Learning Journal, vol. 7, 2026, pp. TBD.
Will be presented at the Reinforcement Learning Conference (RLC), Montréal, Quebec, Canada, August 15–17, 2026.
Keywords: Reinforcement Learning, Stochastic Shortest Path, Dead-ends, Model-based RL, Dual
Stochastic Shortest Path (SSP) problems provide a natural framework for goal-oriented reinforcement learning. However, the classical SSP assumption that a proper policy exists (i.e. a policy that reaches the goal with probability 1) can be violated in practice by the presence of dead-ends. When the goal is unreachable from some states, standard undiscounted RL may diverge, while discounted RL can lead to suboptimal goal-reaching behavior. This paper addresses these challenges by introducing Finite-Penalty Q-learning and Dual Dyna-Q, two algorithms designed to handle SSPs with dead-ends. We evaluate our methods across a variety of grid navigation and symbolic planning (Probabilistic PDDL) benchmarks, demonstrating that they reliably reach the goal while maintaining cost efficiency, significantly outperforming standard model-free and discounted baseline solutions in environments with dead-ends.
Gustavo De Mari Pereira and Leliane N. de Barros. "Goal-Oriented Reinforcement Learning for Stochastic Shortest Paths with Dead-Ends." Reinforcement Learning Journal, vol. 7, 2026, pp. TBD.
BibTeX:@article{pereira2026goaloriented,
title={Goal-Oriented Reinforcement Learning for Stochastic Shortest Paths with Dead-Ends},
author={Gustavo De Mari Pereira and Leliane N. de Barros},
journal={Reinforcement Learning Journal},
volume={7},
pages={},
year={2026}
}