Approaches to goal recognition have progressively relaxed the requirements about the amount of domain knowledge and available observations, yielding accurate and efficient algorithms capable of recognizing goals. However, to recognize goals in raw data, recent approaches require either human engineered domain knowledge, or samples of behavior that account for almost all actions being observed to infer possible goals. This is clearly too strong a requirement for real-world applications of goal recognition, and we develop an approach that leverages advances in recurrent neural networks to perform goal recognition as a classification task, using encoded plan traces for training. We empirically evaluate our approach against the state-of-the-art in goal recognition with image-based domains, and discuss under which conditions our approach is superior to previous ones.

Reinforcement learning (RL) algorithms are often used to compute agents capable of acting in environments without prior knowledge of the environment dynamics. However, these algorithms struggle to converge in environments with large branching factors and their large resulting state-spaces. In this work, we develop an approach to compress the number of entries in a Q-value table using a deep auto-encoder. We develop a set of techniques to mitigate the large branching factor problem. We present the application of such techniques in the scenario of a real-time strategy (RTS) game, where both state space and branching factor are a problem. We empirically evaluate an implementation of the technique to control agents in an RTS game scenario where classical RL fails and provide a number of possible avenues of further work on this problem.

No abstract

Most approaches for goal recognition rely on specifications of the possible dynamics of the actor in the environment when pursuing a goal. These specifications suffer from two key issues. First, encoding these dynamics requires careful design by a domain expert, which is often not robust to noise at recognition time. Second, existing approaches often need costly real-time computations to reason about the likelihood of each potential goal. In this paper, we develop a framework that combines model-free reinforcement learning and goal recognition to alleviate the need for careful, manual domain design, and the need for costly online executions. This framework consists of two main stages: Offline learning of policies or utility functions for each potential goal, and online inference. We provide a first instance of this framework using tabular Q-learning for the learning stage, as well as three measures that can be used to perform the inference stage. The resulting instantiation achieves state-of-the-art performance against goal recognizers on standard evaluation domains and superior performance in noisy environments.

Recent approaches to goal recognition have progressively relaxed the requirements about the amount of domain knowledge and available observations, yielding accurate and efficient algorithms. These approaches, however, assume that there is a domain expert capable of building complete and correct domain knowledge to successfully recognize an agent's goal. This is too strong for most real-world applications. We overcome these limitations by combining goal recognition techniques from automated planning, and deep autoencoders to carry out unsupervised learning to generate domain theories from data streams and use the resulting domain theories to deal with incomplete and noisy observations. Moving forward, we aim to develop a new data-driven goal recognition technique that infers the domain model using the same set of observations used in recognition itself.