Latest Jobs Posted
Job details |
||||||||||||||||||||||||||
|
Job Offer: Research Associate:Job description:Job location: Edinburgh Grade UE07 - £39,347 - £46,974 per annum Full time - 35 hours per week Fixed term contract - 12 months We invite applications for a Research Associate in Deep Learning, Machine Learning Methods and Reinforcement Learning, to work with Prof Amos Storkey, Dr Peter Bell, and Dr Stefano Albrecht. The School of Informaticsis one of the largest research centres in Computer Science in Europe, and has beenranked #1 in the UKin terms of research power by a large margin. Informatics, Edinburgh is world renowned in Machine Learning and Reinforcement Learning, publishing in the top venues in these fields. We are offering an exciting opportunity to work in an interdisciplinary, collaborative, friendly, and supportive environment, integrating different sub-fields of within Artificial Intelligence (AI). Reinforcement learning (RL) algorithms aim to train a decision policy for an agent to achieve a specified task in an environment. The agent's policy is trained by choosing actions which maximise the cumulative compensates received by the agent from its environment. With the introduction of deep learning into RL, ?deep RL? algorithms have achieved unprecedented scalcapability, enabling the solution of complex decision tasks, such as autonomous driving [1] and beating human champions in games such as Go [2]. However, a current limitation of deep RL is that the training process typically requires orders of many millions of environment interactions in the precise environment (i.e. training data), which is infeasible in real-world applications where obtaining samples poses a significant bottleneck. Good transfercapability between different related environments is also still not generally achievable. Thus, developing approaches to improve the sample efficiency of deep RL algorithms, i.e. learning good policies with minimal data or from information learnt elsewhere, is a high-priority research topic. Akin to the idea that, for humans, reading the rules of e.g. a board game helps a person play that game better and more immediately than just doing random things and seeing what happens, in this project we consider the benefit of multimodal image and textual sources for data efficient RL. The researcher will be involved in deploying multimodal benchmarks for RL, and developing integrative models that can understand the implication of textual cues to aid knowledge of the environment, the action space, the compensate space, and the potential policy space. This method will utilise recent approaches in contrastive learning to aid this. Your expertise and attributes for success: » PhD (or near completion) or equivalent research practice in AI, machine learning methods, machine learning in language processing, reinforcement learning or a related discipline. » practice and evidence of effective independent research work within a research team, and contribution to the team effort. » Demonstrated quality of research performance, as evidenced by high-quality publications in top-tier machine learning / computer vision, RL or related venues (e.g., ICML, NeurIPS, ICLR, AISTATS, UAI, AAAI, ACL, EMNLP, ICCV, ECCV, CVPR, and significant journals (IEEE PAMI, JMLR among others). » Strong programming expertise; practice with Python and deep learning libraries (e.g., PyTorch or TensorFlow). Skills:
|
||||||||||||||||||||||||||
|