Caspar Oesterheld

Suppose that an altruistic agent who is uncertain between evidential and causal decision theory finds herself in a situation where these theories give conflicting verdicts. We argue that even if she has significantly higher credence in CDT, she should nevertheless act in accordance with EDT. First, we claim that the appropriate response to normative uncertainty is to hedge one's bets. That is, if the stakes are much higher on one theory than another, and the credences you assign to each of these theories are not very different, then it is appropriate to choose the option that performs best on the high-stakes theory. Second, we show that, given the assumption of altruism, the existence of correlated decision makers will increase the stakes for EDT but leave the stakes for CDT unaffected. Together these two claims imply that whenever there are sufficiently many correlated agents, the appropriate response is to act in accordance with EDT.

Newcomb’s problem has spawned a debate about which variant of expected utility maximisation should guide rational choice. In this paper, we provide a new argument against what is probably the most popular variant: causal decision theory. In particular, we provide two scenarios in which CDT voluntarily loses money. In the first, an agent faces a single choice and following CDT’s recommendation yields a loss of money in expectation. The second scenario extends the first to a diachronic Dutch book against CDT.

Decision theorists disagree about how instrumentally rational agents, i.e., agents trying to achieve some goal, should behave in so-called Newcomb-like problems, with the main contenders being causal and evidential decision theory. Since the main goal of artificial intelligence research is to create machines that make instrumentally rational decisions, the disagreement pertains to this field. In addition to the more philosophical question of what the right decision theory is, the goal of AI poses the question of how to implement any given decision theory in an AI. For example, how would one go about building an AI whose behavior matches evidential decision theory’s recommendations? Conversely, we can ask which decision theories describe the behavior of any existing AI design. In this paper, we study what decision theory an approval-directed agent, i.e., an agent whose goal it is to maximize the score it receives from an overseer, implements. If we assume that the overseer rewards the agent based on the expected value of some von Neumann–Morgenstern utility function, then such an approval-directed agent is guided by two decision theories: the one used by the agent to decide which action to choose in order to maximize the reward and the one used by the overseer to compute the expected utility of a chosen action. We show which of these two decision theories describes the agent’s behavior in which situations.

One approach to achieving cooperation in the one-shot prisoner’s dilemma is Tennenholtz’s (Games Econ Behav 49(2):363–373, 2004) program equilibrium, in which the players of a game submit programs instead of strategies. These programs are then allowed to read each other’s source code to decide which action to take. As shown by Tennenholtz, cooperation is played in an equilibrium of this alternative game. In particular, he proposes that the two players submit the same version of the following program: cooperate if the opponent is an exact copy of this program and defect otherwise. Neither of the two players can benefit from submitting a different program. Unfortunately, this equilibrium is fragile and unlikely to be realized in practice. We thus propose a new, simple program to achieve more robust cooperative program equilibria: cooperate with some small probability

Most ethical work is done at a low level of formality. This makes practical moral questions inaccessible to formal and natural sciences and can lead to misunderstandings in ethical discussion. In this paper, we use Bayesian inference to introduce a formalization of preference utilitarianism in physical world models, specifically cellular automata. Even though our formalization is not immediately applicable, it is a first step in providing ethics and ultimately the question of how to “make the world better” with a formal basis