Learning When To Switch: Adaptive Policy Selection Via Reinforcement Learning

Abstract

Autonomous agents often require multiple strategies to solve complex tasks, but determining when to switch between strategies remains challenging. This research introduces a reinforcement learning technique to learn switching thresholds between two orthogonal navigation policies. Using maze navigation as a case study, this work demonstrates how an agent can dynamically transition between systematic exploration (coverage) and goal-directed pathfinding (convergence) to improve task performance. Unlike fixed-threshold approaches, the agent uses Q-learning to adapt switching behavior based on coverage percentage and distance to goal, requiring only minimal domain knowledge: maze dimensions and target location. The agent does not require prior knowledge of wall positions, optimal threshold values, or hand-crafted heuristics; instead, it discovers effective switching strategies dynamically during each run. The agent discretizes its state space into coverage and distance buckets, then adapts

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytava2025learning

Related papers

• Reinforcement Learning With A Focus On Adjusting Policies To Reach Targets (2024)0.00
• Learning To Switch Among Agents In A Team Via 2-layer Markov Decision Processes (2020)0.00
• Continuously Discovering Novel Strategies Via Reward-switching Policy Optimization (2022)0.00
• Never Give Up: Learning Directed Exploration Strategies (2020)0.00
• When Should Agents Explore? (2021)0.00
• Dynamic Subgoal-based Exploration Via Bayesian Optimization (2019)0.00
• Learning Adaptive Exploration Strategies In Dynamic Environments Through Informed Policy Regularization (2020)0.00
• Post-convergence Sim-to-real Policy Transfer: A Principled Alternative To Cherry-picking (2025)0.00