no code implementations • 20 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.
1 code implementation • 26 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.
1 code implementation • 26 Jan 2023 • Xiulei Song, Yizhao Jin, Greg Slabaugh, Simon Lucas
Estimation of value in policy gradient methods is a fundamental problem.
no code implementations • 11 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.
no code implementations • 15 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.
no code implementations • 12 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).
no code implementations • 18 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.
no code implementations • 15 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.
1 code implementation • 10 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.
1 code implementation • 31 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.
1 code implementation • 23 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.
no code implementations • 23 Mar 2020 • James Goodman, Simon Lucas
The N-Tuple Bandit Evolutionary Algorithm (NTBEA) has proven very effective in optimising algorithm parameters in Game AI.
no code implementations • 6 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
1 code implementation • 3 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.
1 code implementation • 4 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.