Evaluating Generalisation in General Video Game Playing

2020-05-22 · Martin Balla, Simon M. Lucas, Diego Perez-Liebana

The General Video Game Artificial Intelligence (GVGAI) competition has been running for several years with various tracks. This paper focuses on the challenge of the GVGAI learning track in which 3 games are selected and 2 levels are given for training, while 3 hidden levels are left for evaluation. This setup poses a difficult challenge for current Reinforcement Learning (RL) algorithms, as they typically require much more data. This work investigates 3 versions of the Advantage Actor-Critic (A2C) algorithm trained on a maximum of 2 levels from the available 5 from the GVGAI framework and compares their performance on all levels. The selected sub-set of games have different characteristics, like stochasticity, reward distribution and objectives. We found that stochasticity improves the generalisation, but too much can cause the algorithms to fail to learn the training levels. The quality of the training levels also matters, different sets of training levels can boost generalisation over all levels. In the GVGAI competition agents are scored based on their win rates and then their scores achieved in the games. We found that solely using the rewards provided by the game might not encourage winning.

📄 PDF Abstract BibTeX arXiv:2005.11247

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning (RL)

Reinforcement Learning with Dual-Observation for General Video Game Playing

2020-11-11 · Chengpeng Hu, Ziqi Wang, Tianye Shu, Hao Tong 외

Reinforcement learning algorithms have performed well in playing challenging board and video games. More and more studies focus on improving the generalisation ability of reinforcement learning algorithms. The General Vi…

Decision Making reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

General Video Game AI: a Multi-Track Framework for Evaluating Agents, Games and Content Generation Algorithms

2018-02-28 · Diego Perez-Liebana, Jialin Liu, Ahmed Khalifa, Raluca D. Gaina 외

General Video Game Playing (GVGP) aims at designing an agent that is capable of playing multiple video games with no human intervention. In 2014, The General Video Game AI (GVGAI) competition framework was created and re…

Shallow decision-making analysis in General Video Game Playing

2018-06-04 · 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 a…

AI Agent Decision Making Descriptive

Options as responses: Grounding behavioural hierarchies in multi-agent RL

2019-06-04 · Alexander Sasha Vezhnevets, Yuhuai Wu, Remi Leblond, Joel Z. Leibo

This paper investigates generalisation in multi-agent games, where the generality of the agent can be evaluated by playing against opponents it hasn't seen during training. We propose two new games with concealed informa…

Deep Reinforcement Learning Multi-agent Reinforcement Learning Reinforcement Learning Reinforcement Learning (RL)

OPtions as REsponses: Grounding behavioural hierarchies in multi-agent reinforcement learning

2020-01-01 · ICML 2020 1 · Alexander Vezhnevets, Yuhuai Wu, Maria Eckstein, Rémi Leblond 외

Deep Reinforcement Learning Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)