Lukas Schäfer

Lukas Schäfer
The University of Edinburgh | UoE · School of Informatics

PhD Data Science and Artificial Intelligence

About

10
Publications
1,589
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2
Citations
Introduction
In order to learn effective behaviour in multi-agent systems, efficient exploration techniques beyond simple, randomised policies are required. My research aims to investigate novel methods with a particular focus on intrinsic rewards as exploration incentives. Such self-assigned rewards serve as additional feedback to motivate guided exploration, which could enable collaborative behaviour for multi-agent reinforcement learning.
Additional affiliations
October 2019 - present
The University of Edinburgh
Position
  • Research Assistant
Description
  • Designing reinforcement learning (RL) project covering wide range of topics including dynamic programming, single- and multi-agent RL as well as deep RL
September 2017 - October 2017
Universität des Saarlandes
Position
  • Lecturer
Description
  • - Explained importance of mathematics for CS, formal languages and predicate logic to ~250 participants in daily lectures of the first week - Supervised two groups to provide feedback and further assistance in daily coaching-sessions
October 2016 - March 2017
Universität des Saarlandes
Position
  • Research Assistant
Description
  • Taught first-year students fundamental concepts of functional programming, basic complexity theory and inductive correctness proofs in weekly tutorials and office hours
Education
September 2018 - August 2019
The University of Edinburgh
Field of study
  • Informatics
October 2015 - September 2018
Universität des Saarlandes
Field of study
  • Computer Science

Publications

Publications (10)
Preprint
Full-text available
The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group develops novel machine learning algorithms for autonomous systems control, with a specific focus on deep reinforcemen...
Preprint
Successful deployment of multi-agent reinforcement learning often requires agents to adapt their behaviour. In this work, we discuss the problem of teamwork adaptation in which a team of agents needs to adapt their policies to solve novel tasks with limited fine-tuning. Motivated by the intuition that agents need to be able to identify and distingu...
Preprint
Full-text available
Learning control from pixels is difficult for reinforcement learning (RL) agents because representation learning and policy learning are intertwined. Previous approaches remedy this issue with auxiliary representation learning tasks, but they either do not consider the temporal aspect of the problem or only consider single-step transitions. Instead...
Preprint
Full-text available
This paper considers how to complement offline reinforcement learning (RL) data with additional data collection for the task of policy evaluation. In policy evaluation, the task is to estimate the expected return of an evaluation policy on an environment of interest. Prior work on offline policy evaluation typically only considers a static dataset....
Preprint
Full-text available
Deep reinforcement learning (RL) agents that exist in high-dimensional state spaces, such as those composed of images, have interconnected learning burdens. Agents must learn an action-selection policy that completes their given task, which requires them to learn a representation of the state space that discerns between useful and useless informati...
Preprint
Intrinsic rewards are commonly applied to improve exploration in reinforcement learning. However, these approaches suffer from instability caused by non-stationary reward shaping and strong dependency on hyperparameters. In this work, we propose Decoupled RL (DeRL) which trains separate policies for exploration and exploitation. DeRL can be applied...
Preprint
Multi-agent deep reinforcement learning (MARL) suffers from a lack of commonly-used evaluation tasks and criteria, making comparisons between approaches difficult. In this work, we evaluate and compare three different classes of MARL algorithms (independent learners, centralised training with decentralised execution, and value decomposition) in a d...
Preprint
Exploration in multi-agent reinforcement learning is a challenging problem, especially in environments with sparse rewards. We propose a general method for efficient exploration by sharing experience amongst agents. Our proposed algorithm, called Shared Experience Actor-Critic (SEAC), applies experience sharing in an actor-critic framework. We eval...
Thesis
Full-text available
Multi-agent reinforcement learning has seen considerable achievements on a variety of tasks. However, suboptimal conditions involving sparse feedback and partial ob- servability, as frequently encountered in applications, remain a significant challenge. In this thesis, we apply curiosity as exploration bonuses to such multi-agent systems and analyse...
Thesis
Full-text available
This thesis transfers and evaluates the work of Action Schema Networks (ASNets) for domain-dependent policy learning for classical automated planning. First, we will intro- duce the foundational background of automated planning and deep learning in the form of neural networks. Subsequently, the structure and learning of ASNets will be explained as...

Network

Projects

Project (1)
Project
Research intrinsic rewards as exploration incentives to motivate guided, collaborative exploration for multi-agent reinforcement learning.