Search Results for author: Simon Lucas

Found 15 papers, 7 papers with code

ADAPTER-RL: Adaptation of Any Agent using Reinforcement Learning

no code implementations20 Nov 2023 Yizhao Jin, Greg Slabaugh, Simon Lucas

Deep Reinforcement Learning (DRL) agents frequently face challenges in adapting to tasks outside their training distribution, including issues with over-fitting, catastrophic forgetting and sample inefficiency.

reinforcement-learning

Joint action loss for proximal policy optimization

1 code implementation26 Jan 2023 Xiulei Song, Yizhao Jin, Greg Slabaugh, Simon Lucas

Instead, for each sub-action we calculate the loss separately, which is less prone to clipping during updates thereby making better use of samples.

Dota 2

Visualising Multiplayer Game Spaces

no code implementations11 Feb 2022 James Goodman, Diego Perez-Liebana, Simon Lucas

We compare four different `game-spaces' in terms of their usefulness in characterising multi-player tabletop games, with a particular interest in any underlying change to a game's characteristics as the number of players changes.

Dimensionality Reduction

Rinascimento: searching the behaviour space of Splendor

no code implementations15 Jun 2021 Ivan Bravi, Simon Lucas

One of the main purposes of play-testing a game is gathering data on the gameplay, highlighting good and bad features of the design of the game, providing useful insight to the game designers for improving the design.

Griddly: A platform for AI research in games

no code implementations12 Nov 2020 Chris Bamford, Shengyi Huang, Simon Lucas

In recent years, there have been immense breakthroughs in Game AI research, particularly with Reinforcement Learning (RL).

Reinforcement Learning (RL)

AI and Wargaming

no code implementations18 Sep 2020 James Goodman, Sebastian Risi, Simon Lucas

Recent progress in Game AI has demonstrated that given enough data from human gameplay, or experience gained via simulations, machines can rival or surpass the most skilled human players in classic games such as Go, or commercial computer games such as Starcraft.

Starcraft

Does it matter how well I know what you're thinking? Opponent Modelling in an RTS game

no code implementations15 Jun 2020 James Goodman, Simon Lucas

We show that faced with an unknown opponent and a low computational budget it is better not to use any explicit model with RHEA, and to model the opponent's actions within the tree as part of the MCTS algorithm.

Rinascimento: using event-value functions for playing Splendor

1 code implementation10 Jun 2020 Ivan Bravi, Simon Lucas

These events are processed by an Event-value Function (EF) that assigns a value to a single action or a sequence.

Interactive Evolution and Exploration Within Latent Level-Design Space of Generative Adversarial Networks

1 code implementation31 Mar 2020 Jacob Schrum, Jake Gutierrez, Vanessa Volz, Jialin Liu, Simon Lucas, Sebastian Risi

A user study shows that both the evolution and latent space exploration features are appreciated, with a slight preference for direct exploration, but combining these features allows users to discover even better levels.

Neural Game Engine: Accurate learning of generalizable forward models from pixels

1 code implementation23 Mar 2020 Chris Bamford, Simon Lucas

Access to a fast and easily copied forward model of a game is essential for model-based reinforcement learning and for algorithms such as Monte Carlo tree search, and is also beneficial as a source of unlimited experience data for model-free algorithms.

Model-based Reinforcement Learning OpenAI Gym

Weighting NTBEA for Game AI Optimisation

no code implementations23 Mar 2020 James Goodman, Simon Lucas

The N-Tuple Bandit Evolutionary Algorithm (NTBEA) has proven very effective in optimising algorithm parameters in Game AI.

Specificity

Mek: Mechanics Prototyping Tool for 2D Tile-Based Turn-Based Deterministic Games

no code implementations6 Apr 2019 Rokas Volkovas, Michael Fairbank, John Woodward, Simon Lucas

There are few digital tools to help designers create game mechanics.

Programming Languages Human-Computer Interaction

Rinascimento: Optimising Statistical Forward Planning Agents for Playing Splendor

1 code implementation3 Apr 2019 Ivan Bravi, Simon Lucas, Diego Perez-Liebana, Jialin Liu

Game-based benchmarks have been playing an essential role in the development of Artificial Intelligence (AI) techniques.

Shallow decision-making analysis in General Video Game Playing

1 code implementation4 Jun 2018 Ivan Bravi, Jialin Liu, Diego Perez-Liebana, Simon Lucas

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, hyper heuristic based or knowledge based algorithms.

Decision Making Descriptive

Cannot find the paper you are looking for? You can Submit a new open access paper.