Principled reward shaping for reinforcement learning via lyapunov stability theory
Yunlong Dong, Xiuchuan Tang, Ye Yuan
Topics & Concepts
Reinforcement learningConvergence (economics)Lyapunov functionComputer scienceMathematical optimizationStability (learning theory)Function (biology)Bellman equationProcess (computing)Invariant (physics)Control theory (sociology)MathematicsArtificial intelligenceControl (management)Machine learningNonlinear systemEconomicsBiologyOperating systemEvolutionary biologyMathematical physicsPhysicsQuantum mechanicsEconomic growthReinforcement Learning in RoboticsGene Regulatory Network AnalysisNeural dynamics and brain function