Transfer learning has proven to be a wildly successful approach for speeding up reinforcement learning. Techniques often use low-level information obtained in the source task to a...
Tim Brys, Anna Harutyunyan, Matthew E. Taylor, Ann...
Consider a good (such as a hotel room) which, if not sold on time, is worth nothing to the seller. For a customer who is considering a choice of such goods, their prices may chang...
Partially observable Markov decision processes (POMDPs) provide a natural framework to design applications that continuously make decisions based on noisy sensor measurements. The...
In this work we propose a decision-theoretic approach to Intelligent Tutoring Systems (ITSs) that seeks to alleviate the need for extensive development and hand-tuning in the desi...
The streams of tweets from and to the Twitter account of urban transport operators have been considered. A computational module has been designed and developed in order to collect ...
The computer-based simulation of military tactics has largely involved the use of platform-dependent scripting resulting in behaviour that is limited, and difficult to debug and r...
Using an affective agent to estimate humans’ composite emotions is important for creating believable interactions in human-agent collectives. However, there is a lack of suitab...
In order to achieve a human-like skill level in manipulation, autonomous robots that perform everyday manipulation tasks require perception capabilities that go beyond recognition...
Ferenc Balint-Benczedi, Thiemo Wiedemeyer, Moritz ...
Methods for planning in multiagent settings often model other agents’ possible behaviors. However, the space of these models – whether these are policy trees, finite-state co...