State-of-the-art personal robots need to perform complex manipulation tasks to be viable in assistive scenarios. However, many of these robots, like the PR2, use manipulators with high degrees-of-freedom, and the problem is made worse in bimanual manipulation tasks. The complexity of these robots lead to large dimensional state spaces, which are difficult to learn in. We reduce the state space by using demonstrations to discover a representative low-dimensional hyperplane in which to learn. This allows the agent to converge quickly to a good policy. We call this Dimensionality Reduced Reinforcement Learning (DRRL). However, when performing dimensionality reduction, not all dimensions can be fully represented. We extend this work by first learning in a single dimension, and then transferring that knowledge to a higher-dimensional hyperplane.

This paper proposes a reinterpretation of selective attention as a form of control of working memory based on self-generated reward signals and model-free reinforcement learning.

In recent artificial intelligence (AI) research, convolutional neural networks (CNNs) can create artificial agents capable of self-learning. Self-learning autonomous moving objects utilize machine vision techniques based on processing and recognizing objects in digital images. Afterwards, deep reinforcement learning (Deep-RL) is applied to understand and learn intelligent actions and controls. The objective of our research is to study methods and designs on how machine vision and deep machine learning algorithms can be implemented in a virtual world (e.g., a computer game) for moving objects (e.g., vehicles or aircrafts) to improve their navigation and detection of threats in real life. In this paper, we create a framework for generating and using data from computer games to be used in CNNs and Deep-RL to perform intelligent actions. We show the initial results of applying the framework and identify various military applications that may benefit from this research.

Social interacting is a complex task for which machine learning holds particular promise. However, as no sufficiently accurate simulator of human interactions exists today, the learning of social interaction strategies has to happen online in the real world. Actions executed by the robot impact on humans, and as such have to be carefully selected, making it impossible to rely on random exploration. Additionally, no clear reward function exists for social interactions. This implies that traditional approaches used for Reinforcement Learning cannot be directly applied for learning how to interact with the social world. As such we argue that robots will profit from human expertise and guidance to learn social interactions. However, as the quantity of input a human can provide is limited, new methods have to be designed to use human input more efficiently. In this paper we describe a setup in which we combine a framework called Supervised Progressively Autonomous Robot Competencies (SPARC), which allows safer online learning with Reinforcement Learning, with the use of partial states rather than full states to accelerate generalisation and obtain a usable action policy more quickly.

Robots interacting with humans often have to represent and reason with different descriptions of incomplete domain knowledge and uncertainty, and revise this knowledge over time. Towards achieving these capabilities, the architecture described in this paper combines the complementary strengths of declarative programming, probabilistic graphical models, and reinforcement learning. For any given goal, non-monotonic logical reasoning with a coarse-resolution representation of the domain is used to compute a tentative plan of abstract actions. Each abstract action is implemented as a sequence of concrete actions by reasoning probabilistically over the relevant part of a fine-resolution representation tightly-coupled to the coarse-resolution representation. The outcomes of executing the concrete actions are used for subsequenct reasoning at the coarse resolution. Furthermore, the task of interactively learning axioms governing action capabilities, preconditions and effects, is posed as a relational reinforcement learning problem, using decision tree regression and sampling to construct and generalize over candidate axioms. These capabilities are illustrated in simulation and on a physical robot moving objects to specific people or locations in an indoor domain.

Learning from demonstration is a popular method for teaching robots new skills. However, little work has looked at how to measure safety in the context of learning from demonstrations. We discuss three different types of safety problems that are important for robot learning from human demonstrations: (1) using demonstrations to evaluate the safety of a robot's current policy, (2) using demonstrations to enable risk-aware policy improvement, and (3) determining when the demonstrations received by the robot are sufficient to ensure a desired safety level. We propose a risk-aware Bayesian sampling approach based on inverse reinforcement learning that provides a first step towards addressing these problems. We demonstrate the validity of our approach on a simulated navigation task and discuss promising areas for future work.

In this work, we look at the challenge of learning in an action game,Infinite Mario. Learning to play an action game can be divided intotwo distinct but related problems, learning an object-relatedbehavior and selecting a primitive action. We propose a framework that allows for the use of reinforcement learning for both ofthese problems. We present promising results in some instances of thegame and identify some problems that might affect learning.

We present CLASSQ-L (for: class Q-learning) an application of the Q-learning reinforcement learning algorithm to play complete Wargus games. Wargus is a real-time strategy game where players control armies consisting of units of different classes (e.g., archers, knights). CLASSQ-L uses a single table for each class of unit so that each unit is controlled and updates its class' Q-table. This enables rapid learning as in Wargus there are many units of the same class.

One of the major weaknesses of current real-time strategy (RTS) game agents is handling spatial reasoning at a high level. One challenge in developing spatial reasoning modules for RTS agents is to evaluate the ability of a given agent for this competency due to the inevitable confounding factors created by the complexity of these agents. We propose a simplified game that mimics spatial reasoning aspects of more complex games, while removing other complexities. Within this framework, we analyze the effectiveness of classical reinforcement learning for spatial management in order to build a detailed evaluative standard across a broad set of opponent strategies. We show that against a suite of opponents with fixed strategies, basic Q-learning is able to learn strategies to beat each. In addition, we demonstrate that performance against unseen strategies improves with prior training from other distinct strategies. We also test a modification of the basic algorithm to include multiple actors, to speed learning and increase scalability. Finally, we discuss the potential for knowledge transfer to more complex games with similar components.

The strategies for interactive characters to select appropriate dialogues remain as an open issue in related research areas. In this paper we propose an approach based on reinforcement learning to learn the strategy of interrogation dialogue from one virtual agent toward another. The emotion variation of the suspect agent is modeled with a hazard function, and the detective agent must learn its interrogation strategies based on the emotion state of the suspect agent. The reinforcement learning reward schemes are evaluated to choose the proper reward in the dialogue.