Mulitagent Reinforcement Learning in Stochastic Games with Continuous Action Spaces

نویسنده

  • Albert Xin Jiang
چکیده

We investigate the learning problem in stochastic games with continuous action spaces. We focus on repeated normal form games, and discuss issues in modelling mixed strategies and adapting learning algorithms in finite-action games to the continuous-action domain. We applied variable resolution techniques to two simple multi-agent reinforcement learning algorithms PHC and MinimaxQ. Preliminary experiments shows that our variable resolution partitioning method is successful at identifying important regions of the action space while keeping the total number of partitions low.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Stochastic fictitious play with continuous action sets

Continuous action space games form a natural extension to normal form games with finite action sets. However, whilst learning dynamics in normal form games are now well studied, it is not until recently that their continuous action space counterparts have been examined. We extend stochastic fictitious play to the continuous action space framework. In normal form games the limiting behaviour of ...

متن کامل

Reinforcement Learning In Real-Time Strategy Games

We consider the problem of effective and automated decisionmaking in modern real-time strategy (RTS) games through the use of reinforcement learning techniques. RTS games constitute environments with large, high-dimensional and continuous state and action spaces with temporally-extended actions. To operate under such environments we propose Exlos, a stable, model-based MonteCarlo method. Contra...

متن کامل

Learning to Play Mario

Computer Games are interesting test beds for research in Artificial Intelligence and Machine Learning. Games usually have continuous state spaces, large action spaces and are characterized by complex relationships between components. Without applying abstraction and generalizations, learning in computer games domain becomes infeasible. Through this work, we investigate some designs that facilit...

متن کامل

An RL approach to common-interest continuous action games

1. ABSTRACT In this paper we present a reinforcement learning technique based on Learning Automata (LA), more specific Continuous Action Reinforcement Learning Automaton (CARLA), introduced by Howell et. al. in [2]. LA are policy iterators, which have shown good convergence results in discrete action games with independent learners. The approach presented in this paper allows LA to deal with co...

متن کامل

Girsanov Based Direct Policy Gradient Methods

Despite the plethora of reinforcement learning algorithms in machine learning and control, the majority of the work in this area relies on discrete time formulations of stochastic dynamics. In this work we present a new policy gradient algorithm for reinforcement learning in continuous state action spaces and continuous time. The derivation is based on successive application of Girsanov’s theor...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2004