Tony J. Prescott

Reabetswe M. Nkhumise, Debabrota Basu, Tony J. Prescott et al.

The rising successes of RL are propelled by combining smart algorithmic strategies and deep architectures to optimize the distribution of returns and visitations over the state-action space. A quantitative framework to compare the learning processes of these eclectic RL algorithms is currently absent but desired in practice. We address this gap by representing the learning process of an RL algorithm as a sequence of policies generated during training, and then studying the policy trajectory induced in the manifold of state-action occupancy measures. Using an optimal transport-based metric, we measure the length of the paths induced by the policy sequence yielded by an RL algorithm between an initial policy and a final optimal policy. Hence, we first define the 'Effort of Sequential Learning' (ESL). ESL quantifies the relative distance that an RL algorithm travels compared to the shortest path from the initial to the optimal policy. Further, we connect the dynamics of policies in the occupancy measure space and regret (another metric to understand the suboptimality of an RL algorithm), by defining the 'Optimal Movement Ratio' (OMR). OMR assesses the fraction of movements in the occupancy measure space that effectively reduce an analogue of regret. Finally, we derive approximation guarantees to estimate ESL and OMR with finite number of samples and without access to an optimal policy. Through empirical analyses across various environments and algorithms, we demonstrate that ESL and OMR provide insights into the exploration processes of RL algorithms and hardness of different tasks in discrete and continuous MDPs.

Matthew T. Whelan, Tony J. Prescott, Eleni Vasilaki

Hippocampal reverse replay is thought to contribute to learning, and particularly reinforcement learning, in animals. We present a computational model of learning in the hippocampus that builds on a previous model of the hippocampal-striatal network viewed as implementing a three-factor reinforcement learning rule. To augment this model with hippocampal reverse replay, a novel policy gradient learning rule is derived that associates place cell activity with responses in cells representing actions. This new model is evaluated using a simulated robot spatial navigation task inspired by the Morris water maze. Results show that reverse replay can accelerate learning from reinforcement, whilst improving stability and robustness over multiple trials. As implied by the neurobiological data, our study implies that reverse replay can make a significant positive contribution to reinforcement learning, although learning that is less efficient and less stable is possible in its absence. We conclude that reverse replay may enhance reinforcement learning in the mammalian hippocampal-striatal system rather than provide its core mechanism.

Clément Moulin-Frier, Tobias Fischer, Maxime Petit et al.

This paper introduces a cognitive architecture for a humanoid robot to engage in a proactive, mixed-initiative exploration and manipulation of its environment, where the initiative can originate from both the human and the robot. The framework, based on a biologically-grounded theory of the brain and mind, integrates a reactive interaction engine, a number of state-of-the-art perceptual and motor learning algorithms, as well as planning abilities and an autobiographical memory. The architecture as a whole drives the robot behavior to solve the symbol grounding problem, acquire language capabilities, execute goal-oriented behavior, and express a verbal narrative of its own experience in the world. We validate our approach in human-robot interaction experiments with the iCub humanoid robot, showing that the proposed cognitive architecture can be applied in real time within a realistic scenario and that it can be used with naive users.

Samuel Fernando, Roger K. Moore, David Cameron et al.

Automatic speech recognition (ASR) allows a natural and intuitive interface for robotic educational applications for children. However there are a number of challenges to overcome to allow such an interface to operate robustly in realistic settings, including the intrinsic difficulties of recognising child speech and high levels of background noise often present in classrooms. As part of the EU EASEL project we have provided several contributions to address these challenges, implementing our own ASR module for use in robotics applications. We used the latest deep neural network algorithms which provide a leap in performance over the traditional GMM approach, and apply data augmentation methods to improve robustness to noise and speaker variation. We provide a close integration between the ASR module and the rest of the dialogue system, allowing the ASR to receive in real-time the language models relevant to the current section of the dialogue, greatly improving the accuracy. We integrated our ASR module into an interactive, multimodal system using a small humanoid robot to help children learn about exercise and energy. The system was installed at a public museum event as part of a research study where 320 children (aged 3 to 14) interacted with the robot, with our ASR achieving 90% accuracy for fluent and near-fluent speech.