Q-learning in Wumpus World
ثبت نشده
چکیده
Wumpus world is a toy problem domain used in [3] to introduce the concept of logical agents. Using agents that reason about the world with the tools of formal logic is an intuitive approach that underpinned much of the earlier research in artificial intelligence, however there are issues associated with using formal logic as a basis for reasoning (such as the frame problem). I propose to implement an agent that can learn to reason about its environment. Showing that complex reasoning can be internalized by a learning agent allows us to solve problems that are traditionally hard to describe in the language of formal logic.
منابع مشابه
A Comparison of Exploration/Exploitation Techniques for a Q-Learning Agent in the Wumpus World
The Q-Learning algorithm, suggested by Watkins [1], has become one of the most popular reinforcement learning algorithms due to its relatively simple implementation and the complexity reduction gained by the use of a model-free method. However, QLearning does not specify how to trade off exploration of the world for exploitation of the developed policy. Multiple such tradeoffs are possible and ...
متن کاملDFA Learning of Opponent Strategies
This work studies the control of robots in the adversarial world of “Hunt the Wumpus”. The hybrid learning algorithm which controls the robots behavior is a combination of a modified RPNI algorithm, and a utility update algorithm. The modified RPNI algorithm is a DFA learning algorithm, to learn opponents’ strategies. An utility update algorithm is used to quickly derive a successful conclusion...
متن کاملThe Wumpus World in INDIGOLOG: A Preliminary Report
This paper describes an implementation of the the Wumpus World [Russell and Norving, 2003] in INDIGOLOG with the objective of showing the applicability of this interleaved agent programming language for modeling agent behavior in realistic domains. We briefly go over the INDIGOLOG architecture, explain how we can reason about the Wumpus World domain, and show how to express agent behavior using...
متن کاملA SNePS Approach to The Wumpus World Agent or Cassie Meets the Wumpus
We demonstrate the use of SNeRE, the acting component of the SNePS knowledge representation, reasoning, and acting system, by showing its use to implement a wumpus world agent [Russell and Norvig, 1995]1. For this purpose, we use SNePS 2.6.2, which consists of SNePS 2.6.1 [Shapiro et al., 2004] plus some patch files. We usually name our SNePSbased agents Cassie [Shapiro, 1989; 1998; Shapiro and...
متن کاملA Q-learning Based Continuous Tuning of Fuzzy Wall Tracking
A simple easy to implement algorithm is proposed to address wall tracking task of an autonomous robot. The robot should navigate in unknown environments, find the nearest wall, and track it solely based on locally sensed data. The proposed method benefits from coupling fuzzy logic and Q-learning to meet requirements of autonomous navigations. Fuzzy if-then rules provide a reliable decision maki...
متن کامل