Edit: this is now a general index for agent-foundations-related decision
theory research. It is most-recent-first. I’ll add summaries for other posts if anyone wants.
Index
Modal Combat for games other than the prisoner’s dilemma
An open problem relevant to decision theory and to understanding bounded
reasoning: is there a very easily computable prior over logical facts
that, when updated on the results of computations, performs well in some
sense?
Training Garrabrant inductors to predict counterfactuals
A proposal for training UGIs to predict action- and
policy-counterfactuals by learning from the consequences of actions
taken by similar (“logically previous”) agents.
A reference for notation that might be useful for using (universal)
Garrabrant inductors as models for bounded reasoning, and some notation
for modelling agents. (Not on the forum because tables.)
Index of some decision theory posts
author:
‘Tsvi Benson-Tilsen’ title: Index of some decision theory posts …
What this is
Index
Index of some decision theory posts
Notation for induction and decision theory
Desiderata for decision theory
An inductive setting for decision theory
Training a universal Garrabrant inductor to predict counterfactuals
Open problem: very thin logical priors
What this is
Edit: this is now a general index for agent-foundations-related decision theory research. It is most-recent-first. I’ll add summaries for other posts if anyone wants.
Index
Modal Combat for games other than the prisoner’s dilemma
Forum post: https://agentfoundations.org/item?id=1304
Generalizing Foundations of Decision Theory
Forum post: https://agentfoundations.org/item?id=1302
Prediction Based Robust Cooperation
Forum post: https://agentfoundations.org/item?id=1295
Entangled Equilibria and the Twin Prisoners’ Dilemma
Forum post: https://agentfoundations.org/item?id=1279
On motivations for MIRI’s highly reliable agent design research
Forum post: https://agentfoundations.org/item?id=1220
Open problem: very thin logical priors
An open problem relevant to decision theory and to understanding bounded reasoning: is there a very easily computable prior over logical facts that, when updated on the results of computations, performs well in some sense?
Forum post: https://agentfoundations.org/item?id=1206
postCDT: Decision Theory using post-selected Bayes nets
Forum post: https://agentfoundations.org/item?id=1077
Updatelessness and Son of X
Forum post: https://agentfoundations.org/item?id=1073
A failed attempt at Updatelessness using Universal Inductors
Forum post: https://agentfoundations.org/item?id=1071
Training Garrabrant inductors to predict counterfactuals
A proposal for training UGIs to predict action- and policy-counterfactuals by learning from the consequences of actions taken by similar (“logically previous”) agents.
Forum post: https://agentfoundations.org/item?id=1054
Github pdf: https://github.com/tsvibt/public-pdfs/blob/master/decision-theory/training-counterfactuals/main.pdf
Desiderata for decision theory
A list of desiderata for a theory of optimal decision-making for bounded rational agents in general environments.
Forum post: https://agentfoundations.org/item?id=1053
Github pdf: https://github.com/tsvibt/public-pdfs/blob/master/decision-theory/desiderata/main.pdf
Transitive negotiations with counterfactual agents
Forum post: https://agentfoundations.org/item?id=1047
Attacking the grain of truth problem using Bayes-Savage agents
Forum post: https://agentfoundations.org/item?id=1046
Notation for induction and decision theory
A reference for notation that might be useful for using (universal) Garrabrant inductors as models for bounded reasoning, and some notation for modelling agents. (Not on the forum because tables.)
Github pdf: https://github.com/tsvibt/public-pdfs/blob/master/decision-theory/notation/main.pdf
Index of some decision theory posts
As advertised.
Forum post: https://agentfoundations.org/item?id=1026
Github pdf: https://github.com/tsvibt/public-pdfs/blob/master/decision-theory/index/main.pdf