Domain-Independent Optimistic Initialization for Reinforcement Learning

2014/10/16 by Marlos C. Machado, Sriram Srinivasan, Machado, Marlos C. +3 · 1 citation
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #Evolutionary Algorithms and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Reinforcement Learning in Robotics #VLSI and FPGA Design Techniques

paper · pdf · doi:10.48550/arxiv.1410.4604

openalex publication_date 2014/10/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In Reinforcement Learning (RL), it is common to use optimistic initialization of value functions to encourage exploration. However, such an approach generally depends on the domain, viz., the scale of the rewards must be known, and the feature representation must have a constant norm. We present a simple approach that performs optimistic initialization with less dependence on the domain.

Cited by

• Agent-Agnostic Human-in-the-Loop Reinforcement Learning

Related

• Randomized Exploration for Reinforcement Learning with General Value\n Function Approximation
• Optimistic Exploration even with a Pessimistic Initialisation
• On Optimistic versus Randomized Exploration in Reinforcement Learning
• Towards Tractable Optimism in Model-Based Reinforcement Learning
• Minimax Optimal Reinforcement Learning with Quasi-Optimism