Aug 3, 2011

Paper Drafts

Here are draft versions of two short papers. They are on machine ethics and decision theory in the context of reinforcement learning. Comments are welcome.


This article presents a modification of reinforcement learning where an agent’s action lead to rewards being received by a second agent interacting with same environment. This model can be useful in the development of powerful AIs. Agent policies are proposed for dealing with observable rewards, with non-observable rewards in perfectly rational agents, and with non-observable rewards in bounded rational agents.

Newcomblike Problems and Optimal Agents


This article discusses the family of Newcomblike problems in the context of reinforcement learning. It reframes the problem of rational decision making as one of obtaining maximal rewards in a wide range of environments. Newcomblike problems are characterized by correlations between agent and environment policies. An optimal policy, taking into account these correlations, is given for known environments. For unknown environments, a quality criterion for policies is formulated.


Dr. Gerulf Tschurtschenthaler said...

Hello. My name is Dr. Gerulf Tschurtschenthaler from Königsberg University (East Prussia). Ich will to comment on yours article. As I am german likes you, and my english is not rich, please allowen Sie mir to answer in our own language:

Gleichrichter quer Schnitt längs Pressung. Verbot!
Schmierfilmdicke Ölnuten in wenig belasteten Zonen, Strirnräder bei Ausdrehung positiv, bei Stirnteilung negativ.
Die walzgefräßte, -gehobelte, -gestoßene Verzahnung. (Fließpressen bei Lebensgefahr!)
Bei Parallel-Schaltungen von Drosselspule und Kondensator empfiehlt es sich jedoch, die Parallel-Ersatzschaltung der Drosselspule (siehe Abb. 128a) zu benutzen.

Krieg, Gedankenexperiment -> Krummholtz! Vielen Dank.

Mit fr. Grüßen,
Dr. Gerulf Tschurtschenthaler

Dr. Gerulf Tschurtschenthaler said...
This comment has been removed by the author.