Artificial Morality

Peter Danielson, Artificial Morality: Virtuous Robots for Virtual Games. London: Routledge, 1992. 

Available through Amazon (who've lost my cover, I guess:-()
but, unfortunately, not at:

Support

Download the Prolog programs in the book

The appeal to evolutionary game theory in Artificial Morality Chap. 5 is misleading. By focusing very small, hand picked populations and only a few generations, CC appears less robust than it is. Here are some better tools implementing the replicator dynamics over larger larger populations: 

• The first applet tests all combinations of {UC, UD, CC}. Notice that UD never supplants CC.
• The second applet tests all combinations of {UC, UD, CC, RC} Notice that RC does not always supplant CC.

Discussions in Stanford Encyclopedia of Philosophy 

• prisoner's dilemma (Steven Kuhn)
• game theory (Don Ross)

Works citing Artificial Morality

2001 Flordi, Luciano and Sanders, J.W. "On the Morality of Artificial Agents", presented at Computer Ethics: Philosophical Enquiries, Dec 2001.  [Abstract][pdf]

1997 Ahmad, K. Safety-Critical Systems: Prescient, Presignifying, Public-Good Systems? In Felix Redmill and Tom Anderson. (eds.) 'Safer Systems'. Proc. of the Fifth Safety-critical Systems Symposium (Brighton, 4-6 Feb. 1997). London: Springer-Verlag. pp 1-37. (ISBN 3-540-76134-9)

1995. Marsh, S. "Exploring the Socially Adept Agent," in proceedings, First International Workshop on Decentralized Intelligent Multi-Agent Systems (DIMAS'95), Krakow, Poland, pages 301 - 308. PDF