Search Results for author:
Found 15 papers, 4 papers with code
Multi-Agent Risks from Advanced AI
The rapid development of advanced AI agents and the imminent deployment of many instances of these agents will give rise to multi-agent systems of unprecedented complexity.
Computing Game Symmetries and Equilibria That Respect Them
Strategic interactions can be represented more concisely, and analyzed and solved more efficiently, if we are aware of the symmetries within the multiagent system.
Observation Interference in Partially Observable Assistance Games
We show that this incentive for interference goes away if the human is playing optimally, or if we introduce a communication channel for the human to communicate their preferences to the assistant.
Characterising Simulation-Based Program Equilibria
Finally, we explore the limits of simulation-based program equilibrium, showing that the Tennenholtz folk theorem cannot be attained by simulation-based programs without access to shared randomness.
A dataset of questions on decision-theoretic reasoning in Newcomb-like problems
We introduce a dataset of natural-language questions in the decision theory of so-called Newcomb-like problems.
Can CDT rationalise the ex ante optimal policy via modified anthropics?
If so, then causal decision theory might recommend one-boxing in order to cause the predictor to fill the opaque box.
Imperfect-Recall Games: Equilibrium Concepts and Their Complexity
We investigate optimal decision making under imperfect recall, that is, when an agent forgets information it once held before.
Recursive Joint Simulation in Games
In this paper, we study an interaction between AI agents where the agents run a recursive joint simulation.
A Theory of Bounded Inductive Rationality
In this paper, we develop a theory of rational decision making that does not assume logical omniscience.
Incentivizing honest performative predictions with proper scoring rules
We show that, for binary predictions, if the influence of the expert's prediction on outcomes is bounded, it is possible to define scoring rules under which optimal reports are arbitrarily close to fixed points.
The Computational Complexity of Single-Player Imperfect-Recall Games
For such games, two natural equilibrium concepts have been proposed as alternative solution concepts to ex-ante optimality.
For Learning in Symmetric Teams, Local Optima are Global Nash Equilibria
In this work, we show that any locally optimal symmetric strategy profile is also a (global) Nash equilibrium.
Reinforcement Learning in Newcomblike Environments
This gives us a powerful tool for reasoning about the limit behaviour of agents -- for example, it lets us show that there are Newcomblike environments in which a reinforcement learning agent cannot converge to any optimal policy.
A New Formalism, Method and Open Issues for Zero-Shot Coordination
We introduce an extension of the algorithm, other-play with tie-breaking, and prove that it is optimal in the LFC problem and an equilibrium in the LFC game.
Formalizing Preference Utilitarianism in Physical World Models
Most ethical work is done at a low level of formality.
