International Journal of Smart Engineering System Design · 2002 · 11 citations · 9 references
ComputingAutonomous SystemsAlgorithmsArtificial IntelligencePath PlanningAutonomous ExplorationExploration-exploitation TradeoffOptimal ControlPolicy IterationPolicy LearningReinforcement LearningExploitation Trade-offExploration In Reinforcement LearningLearning From ExplorationMulti-agent Path PlanningPenaltiesReinforcement Learning ModelsState-value Function
One much researched issue in reinforcement learning is the trade-off between exploration and exploitation. Being able to effectively balance exploration and exploitation activities becomes even more crucial in a dynamic environment. A learning algorithm is proposed herein that provides one solution to the exploration vs. exploitation dilemma. The algorithm is presented in the context of a path-finding agent in a dynamic grid-world problem. The state-value function used is penalty-based, allowing the agent to act over the space of paths with minimal penalties. A forgetting mechanism is implemented that allows the agent to explore paths that were previously determined to be suboptimal. Simulation results are used to analyze the behavior of the proposed algorithm in a dynamic environment.
9
Reinforcement Learning: An Introduction
Richard S. Sutton, Andy Barto · IEEE Transactions on Neural Networks · 1998 · 27.1K citations
IEEE Control Systems · 2004 · 543 citations
Engineering, Electrical Engineering, Systems Engineering +10
Vision based navigation for an unmanned aerial vehicle
Bruno Sinopoli, Mario Micheli, Guido Walter Di Donato et al. · 2002 · 198 citations