Daniel Furelos-Blanco

PhD Student

Imperial College London

I am second-year PhD student in Computer Science advised by Prof. Alessandra Russo and Dr. Krysia Broda at Imperial College London. Previously, I worked as research assistant at Universitat Pompeu Fabra under the supervision of Dr. Anders Jonsson. The focus of my research was on planning formalisms involving concurrent actions, mainly multiagent planning and temporal planning.


  • Reinforcement Learning
  • Knowledge Representation
  • Automated Planning


  • MSc in Intelligent Interactive Systems, 2017

    Universitat Pompeu Fabra

  • BSc in Computer Engineering, 2015

    Universitat Pompeu Fabra

Recent Publications

Induction of Subgoal Automata for Reinforcement Learning

In this work we present ISA, a novel approach for learning and exploiting subgoals in reinforcement learning (RL). Our method relies on inducing an automaton whose transitions are subgoals expressed as propositional formulas over a set of observable events. A state-of-the-art inductive logic programming system is used to learn the automaton from observation traces perceived by the RL agent. The reinforcement learning and automaton learning processes are interleaved: a new refined automaton is learned whenever the RL agent generates a trace not recognized by the current automaton. We evaluate ISA in several gridworld problems and show that it performs similarly to a method for which automata are given in advance. We also show that the learned automata can be exploited to speed up convergence through reward shaping and transfer learning across multiple tasks. Finally, we analyze the running time and the number of traces that ISA needs to learn an automata, and the impact that the number of observable events has on the learner’s performance.

Solving Multiagent Planning Problems with Concurrent Conditional Effects

In this work we present a novel approach to solving concurrent multiagent planning problems in which several agents act in parallel. Our approach relies on a compilation from concurrent multiagent planning to classical planning, allowing us to use an off-the-shelf classical planner to solve the original multiagent problem. The solution can be directly interpreted as a concurrent plan that satisfies a given set of concurrency constraints, while avoiding the exponential blowup associated with concurrent actions. Our planner is the first to handle action effects that are conditional on what other agents are doing. Theoretically, we show that the compilation is sound and complete. Empirically, we show that our compilation can solve challenging multiagent planning problems that require concurrent actions.

Recent Posts

Wireless Sensor Networks (WSN) using Arduino and XBee

I have decided to write my first real post. I’m going to briefly write about a bunch of projects related to Wireless Sensor …

Welcome to my blog!

Hi everyone! After some months (and even years) thinking about starting my own webpage, I have finally done it. The main reason for …