45 citations · 102 across the 14 of their papers we have counts for
24 papers
Higher Replay Ratio Empowers Sample-Efficient Multi-Agent Reinforcement Learning
Linjie Xu, Zichuan Liu, Alexander Dockhorn +4
One of the notorious issues for Reinforcement Learning (RL) is poor sample efficiency. Compared to single agent RL, the sample efficiency for Multi-Agent Reinforcement Learning (MA…
Elastic Monte Carlo Tree Search with State Abstraction for Strategy Game Playing
Linjie Xu, Jorge Hurtado-Grueso, Dominic Jeurissen +2
Strategy video games challenge AI agents with their combinatorial search space caused by complex game elements. State abstraction is a popular technique that reduces the state spac…
Task Relabelling for Multi-task Transfer using Successor Features
Martin Balla, Diego Perez-Liebana
Deep Reinforcement Learning has been very successful recently with various works on complex domains. Most works are concerned with learning a single policy that solves the target t…
Portfolio Search and Optimization for General Strategy Game-Playing
Alexander Dockhorn, Jorge Hurtado-Grueso, Dominik Jeurissen +2
Portfolio methods represent a simple but efficient type of action abstraction which has shown to improve the performance of search-based agents in a range of strategy games. We fir…
Action Advising with Advice Imitation in Deep Reinforcement Learning
Ercument Ilhan, Jeremy Gow, Diego Perez-Liebana
Action advising is a peer-to-peer knowledge exchange technique built on the teacher-student paradigm to alleviate the sample inefficiency problem in deep reinforcement learning. Re…
Learning on a Budget via Teacher Imitation
Ercument Ilhan, Jeremy Gow, Diego Perez-Liebana
Deep Reinforcement Learning (RL) techniques can benefit greatly from leveraging prior experience, which can be either self-generated or acquired from other entities. Action advisin…
The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors
William H. Guss, Mario Ynocente Castro, Sam Devlin +12
Although deep reinforcement learning has led to breakthroughs in many difficult domains, these successes have required an ever-increasing number of samples, affording only a shrink…
The Design Of "Stratega": A General Strategy Games Framework
Diego Perez-Liebana, Alexander Dockhorn, Jorge Hurtado Grueso +1
Stratega, a general strategy games framework, has been designed to foster research on computational intelligence for strategy games. In contrast to other strategy game frameworks,…
Guaranteeing Reproducibility in Deep Learning Competitions
Brandon Houghton, Stephanie Milani, Nicholay Topin +5
To encourage the development of methods with reproducible and robust training behavior, we propose a challenge paradigm where competitors are evaluated directly on the performance…
Learning Local Forward Models on Unforgiving Games
Alexander Dockhorn, Simon M. Lucas, Vanessa Volz +3
This paper examines learning approaches for forward models based on local cell transition functions. We provide a formal definition of local forward models for which we propose two…
Teaching on a Budget in Multi-Agent Deep Reinforcement Learning
Ercüment İlhan, Jeremy Gow, Diego Perez-Liebana
Deep Reinforcement Learning (RL) algorithms can solve complex sequential decision tasks successfully. However, they have a major drawback of having poor sample efficiency which can…
Rinascimento: Optimising Statistical Forward Planning Agents for Playing Splendor
Ivan Bravi, Simon Lucas, Diego Perez-Liebana +1
Game-based benchmarks have been playing an essential role in the development of Artificial Intelligence (AI) techniques. Providing diverse challenges is crucial to push research to…
The MineRL 2019 Competition on Sample Efficient Reinforcement Learning using Human Priors
William H. Guss, Cayden Codel, Katja Hofmann +9
Though deep reinforcement learning has led to breakthroughs in many difficult domains, these successes have required an ever-increasing number of samples. As state-of-the-art reinf…
Efficient Evolutionary Methods for Game Agent Optimisation: Model-Based is Best
Simon M. Lucas, Jialin Liu, Ivan Bravi +4
This paper introduces a simple and fast variant of Planet Wars as a test-bed for statistical planning based Game AI agents, and for noisy hyper-parameter optimisation. Planet Wars…
Shallow decision-making analysis in General Video Game Playing
Ivan Bravi, Jialin Liu, Diego Perez-Liebana +1
The General Video Game AI competitions have been the testing ground for several techniques for game playing, such as evolutionary computation techniques, tree search algorithms, hy…
The N-Tuple Bandit Evolutionary Algorithm for Game Agent Optimisation
Simon M Lucas, Jialin Liu, Diego Perez-Liebana
This paper describes the N-Tuple Bandit Evolutionary Algorithm (NTBEA), an optimisation algorithm developed for noisy and expensive discrete (combinatorial) optimisation problems.…
The N-Tuple Bandit Evolutionary Algorithm for Automatic Game Improvement
Kamolwan Kunanusont, Raluca D. Gaina, Jialin Liu +2
This paper describes a new evolutionary algorithm that is especially well suited to AI-Assisted Game Design. The approach adopted in this paper is to use observations of AI agents…
Analysis of Vanilla Rolling Horizon Evolution Parameters in General Video Game Playing
Raluca D. Gaina, Jialin Liu, Simon M. Lucas +1
Monte Carlo Tree Search techniques have generally dominated General Video Game Playing, but recent research has started looking at Evolutionary Algorithms and their potential at ma…
Evaluating and Modelling Hanabi-Playing Agents
Joseph Walton-Rivers, Piers R. Williams, Richard Bartle +2
Agent modelling involves considering how other agents will behave, in order to influence your own actions. In this paper, we explore the use of agent modelling in the hidden-inform…
Population Seeding Techniques for Rolling Horizon Evolution in General Video Game Playing
Rauca D. Gaina, Simon M. Lucas, Diego Perez-Liebana
While Monte Carlo Tree Search and closely related methods have dominated General Video Game Playing, recent research has demonstrated the promise of Rolling Horizon Evolutionary Al…
Evolving Game Skill-Depth using General Video Game AI Agents
Jialin Liu, Julian Togelius, Diego Perez-Liebana +1
Most games have, or can be generalised to have, a number of parameters that may be varied in order to provide instances of games that lead to very different player experiences. The…
Rolling Horizon Coevolutionary Planning for Two-Player Video Games
Jialin Liu, Diego Pérez-Liébana, Simon M. Lucas
This paper describes a new algorithm for decision making in two-player real-time video games. As with Monte Carlo Tree Search, the algorithm can be used without heuristics and has…
Optimal resampling for the noisy OneMax problem
Jialin Liu, Michael Fairbank, Diego Pérez-Liébana +1
The OneMax problem is a standard benchmark optimisation problem for a binary search space. Recent work on applying a Bandit-Based Random Mutation Hill-Climbing algorithm to the noi…
Bandit-Based Random Mutation Hill-Climbing
Jialin Liu, Diego Peŕez-Liebana, Simon M. Lucas
The Random Mutation Hill-Climbing algorithm is a direct search technique mostly used in discrete domains. It repeats the process of randomly selecting a neighbour of a best-so-far…