In this paper we present a hybrid system combining techniques from symbolic planning and reinforcement learning. Planning is used to automatically construct task hierarchies for hierarchical reinforcement learning based on abstract models of the behaviours’ purpose, and to perform intelligent termination improvement when an executing behaviour is no longer appropriate. Reinforcement learning is...

This paper presents a comparative analysis of three Reinforcement Learning algorithms (Q-learning, Q(λ)-learning and QSlearning) and their heuristically-accelerated variants (HAQL, HAQ(λ) and HAQS) where heuristics bias action selection, thus speeding up the learning. The experiments were performed in a simulated robot soccer environment which reproduces the conditions of a real competition lea...

In this paper, we propose a memory-based Q-learning algorithm called predictive Q-routing (PQ-routing) for adaptive traac control. We attempt to address two problems encountered in Q-routing (Boyan & Littman, 1994), namely, the inability to ne-tune routing policies under low network load and the inability to learn new optimal policies under decreasing load conditions. Unlike other memory-based ...

Fuzzy logic is a mathematical approach towards the human way of thinking and learning. Based on if-then rules, we can design fuzzy controllers with the intuitive experience of human beings. However, it is not practical for a designer to find necessary number of rules and determine appropriate parameters by hand. Hence, we incorporate a reinforcement learning method with basic fuzzy rules so tha...

In sequential decision making, it is often important and useful for end users to understand the underlying patterns or causes that lead to the corresponding decisions. However, typical deep reinforcement learning algorithms seldom provide such information due to their black-box nature. In this paper, we present a probabilistic model, Q-LDA, to uncover latent patterns in text-based sequential de...

In this work, we introduce a technique that uses stories to train virtual agents to exhibit believable behavior. This technique uses a compact representation of a story to define the space of acceptable behaviors and then uses this space to assign rewards to certain world states. We show the effectiveness of our technique with a case study in a modified gridworld environment called Pharmacy Wor...

The widespread diffusion of mobile phones is triggering an exponential growth of mobile data traffic that is likely to cause, in the near future, considerable traffic overload issues even in last-generation cellular networks. Offloading part of the traffic to other networks is considered a very promising approach and, in particular, in this paper we consider offloading through opportunistic net...

In the paper, we investigate the use of reinforcement learning in CBR for estimating and managing a legacy case base for playing the game of Tetris. Each case corresponds to a local pattern describing the relative height of a subset of columns where pieces could be placed. We evaluate these patterns through reinforcement learning to determine if significant performance improvement can be observ...

Transfer learning significantly accelerates the reinforcement learning process by exploiting relevant knowledge from previous experiences. The problem of optimally selecting source policies during the learning process is of great importance yet challenging. There has been little theoretical analysis of this problem. In this paper, we develop an optimal online method to select source policies fo...

The application of decision making and learning algorithms to multi-agent systems presents many interestingresearch challenges and opportunities. Among these is the ability for agents to learn how to act by observing or imitating other agents. We describe an algorithm, the IQ-algorithm, that integrates imitation with Q-learning. Roughly, a Q-learner uses the observations it has made of an “expe...