Reinforcement learning is a general approach to learning reactive control policies. It is an unsupervised learning technique, making it a candidate for use in system that adapts to changing tasks and environment by autonomously devising a new strategy. Unfortunately, reinforcement learning methods are slow to converge to a solution, rendering them impractical in most cases. The key shortcoming ...

In this paper we present ISA, an approach for learning and exploiting subgoals in episodic reinforcement (RL) tasks. ISA interleaves with the induction of a subgoal automaton, automaton whose edges are labeled by task’s expressed as propositional logic formulas over set high-level events. A also consists two special states: state indicating successful completion task, that task has finished wit...

Deep Reinforcement Learning (DRL) methods have performed well in an increasing numbering of high-dimensional visual decision making domains. Among all such visual decision making problems, those with discrete action spaces often tend to have underlying compositional structure in the said action space. Such action spaces often contain actions such as go left, go up as well as go diagonally up an...

The complexity of most modern systems prohibits a handcoded approach to decision making. In addition, many problems have continuous or large discrete state spaces; some have large or continuous action spaces. The problem of learning in large spaces is tackled through generalisation techniques, which allow compact representation of learned information and transfer of knowledge between similar st...

Dynamic control tasks are good candidates for the application of reinforcement learning techniques. However, many of these tasks inherently have continuous state or action variables. This can cause problems for traditional reinforcement learning algorithms which assume discrete states and actions. In this paper, we introduce an algorithm that safely approximates the value function for continuou...

This paper aims to introduce an effective classification method of learning for partitioning the data in statistical spaces. The work is based on using multi-constraint partitioning on the stochastic learning automata. Stochastic learning automata with fixed or variable structures are a reinforcement learning method. Having no information about optimized operation, such models try to find an an...

Modeling learning agents in the context of Multi-agent Systems requires insight in the type and form of interactions with the environment and other agents in the system. Usually, these agents are modeled similar to the different players in a standard game theoretical model. In this paper we examine whether evolutionary game theory, and more specifically the replicator dynamics, is an adequate t...

This paper presents a general approach to image segmentation and object recognition that can adapt the image segmentation algorithm parameters to the changing environmental conditions. Segmentation parameters are represented by a team of generalized stochastic learning automata and learned using connectionist reinforcement learning techniques. The edge-border coincidence measure is first used a...

Most existing deep reinforcement learning (DRL) frameworks consider action spaces that are either discrete or continuous space. Motivated by the project of design Game AI for King of Glory (KOG), one the world’s most popular mobile game, we consider the scenario with the discrete-continuous hybrid action space. To directly apply existing DLR frameworks, existing approaches either approximate th...