论文信息 - Comparing the Behaviour of Learning Agents - 字舞流文

Comparing the Behaviour of Learning Agents

Evaluating the behaviour of non-player characters is a complex problem. The multifaceted goals of non-player characters include:

Kathryn E. Merrick | Mary Lou Maher

[1] Nilanjan Sarkar,et al. Maintaining Optimal Challenge in Computer Games through Real-Time Physiological Feedback , 2005 .

[2] Juyang Weng,et al. Inherent Value Systems for Autonomous Mental Development , 2007, Int. J. Humanoid Robotics.

[3] Edward Byrne. Game Level Design , 2004 .

[4] Nuttapong Chentanez,et al. Intrinsically Motivated Reinforcement Learning , 2004, NIPS.

[5] Andrew W. Moore,et al. Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[6] Pierre-Yves Oudeyer,et al. Motivational principles for visual know-how development , 2003 .

[7] Richard S. Sutton,et al. Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[8] Rob Saunders,et al. Designing for Interest and Novelty Motivating Design Agents , 2001 .

[9] Bernhard Hengst,et al. Discovering Hierarchy in Reinforcement Learning with HEXQ , 2002, ICML.

[10] Donald A. Berry,et al. Bandit Problems: Sequential Allocation of Experiments. , 1986 .

[11] Georgios N. Yannakakis,et al. Towards Capturing and Enhancing Entertainment in Computer Games , 2006, SETN.

[12] Jürgen Schmidhuber,et al. Exploring the predictable , 2003 .

[13] Jenova Chen,et al. Flow in games (and everything else) , 2007, CACM.