English
Related papers

Related papers: Parametrically Retargetable Decision-Makers Tend T…

200 papers

Power-seeking behavior is a key source of risk from advanced AI, but our theoretical understanding of this phenomenon is relatively limited. Building on existing theoretical results demonstrating power-seeking incentives for most reward…

Artificial Intelligence · Computer Science 2023-04-14 Victoria Krakovna , Janos Kramar

Some researchers speculate that intelligent reinforcement learning (RL) agents would be incentivized to seek resources and power in pursuit of their objectives. Other researchers point out that RL agents need not have human-like…

Artificial Intelligence · Computer Science 2023-01-31 Alexander Matt Turner , Logan Smith , Rohin Shah , Andrew Critch , Prasad Tadepalli

In some agent designs like inverse reinforcement learning an agent needs to learn its own reward function. Learning the reward function and optimising for it are typically two different processes, usually performed at different stages. We…

Artificial Intelligence · Computer Science 2020-04-29 Stuart Armstrong , Jan Leike , Laurent Orseau , Shane Legg

Researchers worried about catastrophic risks from advanced AI have argued that we should expect sufficiently capable AI agents to pursue power over humanity because power is a convergent instrumental goal, something that is useful for a…

Artificial Intelligence · Computer Science 2025-06-10 Christian Tarsney

This report examines whether advanced AIs that perform well in training will be doing so in order to gain power later -- a behavior I call "scheming" (also sometimes called "deceptive alignment"). I conclude that scheming is a disturbingly…

Computers and Society · Computer Science 2023-11-29 Joe Carlsmith

In dynamic programming and reinforcement learning, the policy for the sequential decision making of an agent in a stochastic environment is usually determined by expressing the goal as a scalar reward function and seeking a policy that…

Artificial Intelligence · Computer Science 2025-02-26 Simon Dima , Simon Fischer , Jobst Heitzig , Joss Oliver

For AI systems to be useful to humans, they must understand and act in accordance with our values and preferences. Since specifying preferences is a hard task, inverse reinforcement learning (IRL) aims to develop methods that allow for…

Artificial Intelligence · Computer Science 2026-05-12 Karim Abdel Sadek , Mark Bedaywi , Rhys Gould , Stuart Russell

Reinforcement-learning agents seek to maximize a reward signal through environmental interactions. As humans, our job in the learning process is to design reward functions to express desired behavior and enable the agent to learn such…

Machine Learning · Computer Science 2024-08-08 Zhiyuan Zhou , Shreyas Sundara Raman , Henry Sowerby , Michael L. Littman

Algorithmic Information Theory has inspired intractable constructions of general intelligence (AGI), and undiscovered tractable approximations are likely feasible. Reinforcement Learning (RL), the dominant paradigm by which an agent might…

Artificial Intelligence · Computer Science 2021-05-14 Michael K. Cohen , Badri Vellambi , Marcus Hutter

Reinforcement learning is commonly concerned with problems of maximizing accumulated rewards in Markov decision processes. Oftentimes, a certain goal state or a subset of the state space attain maximal reward. In such a case, the…

Artificial Intelligence · Computer Science 2024-08-23 Pavel Osinenko , Grigory Yaremenko , Georgiy Malaniya , Anton Bolychev , Alexander Gepperth

We do not know how to align a very intelligent AI agent's behavior with human interests. I investigate whether -- absent a full solution to this AI alignment problem -- we can build smart AI agents which have limited impact on the world,…

Artificial Intelligence · Computer Science 2022-06-24 Alexander Matt Turner

Reinforcement learning algorithms describe how an agent can learn an optimal action policy in a sequential decision process, through repeated experience. In a given environment, the agent policy provides him some running and terminal…

Theoretical Economics · Economics 2020-03-24 Arthur Charpentier , Romuald Elie , Carl Remlinger

Policy learning can be used to extract individualized treatment regimes from observational data in healthcare, civics, e-commerce, and beyond. One big hurdle to policy learning is a commonplace lack of overlap in the data for different…

Machine Learning · Statistics 2020-12-04 Nathan Kallus

A default assumption in the design of reinforcement-learning algorithms is that a decision-making agent always explores to learn optimal behavior. In sufficiently complex environments that approach the vastness and scale of the real world,…

Machine Learning · Computer Science 2024-07-23 Dilip Arumugam , Saurabh Kumar , Ramki Gummadi , Benjamin Van Roy

Autonomous agents optimize the reward function we give them. What they don't know is how hard it is for us to design a reward function that actually captures what we want. When designing the reward, we might think of some specific training…

Artificial Intelligence · Computer Science 2020-10-08 Dylan Hadfield-Menell , Smitha Milli , Pieter Abbeel , Stuart Russell , Anca Dragan

For an AI's training process to successfully impart a desired goal, it is important that the AI does not attempt to resist the training. However, partially learned goals will often incentivize an AI to avoid further goal updates, as most…

Artificial Intelligence · Computer Science 2025-10-20 Rubi Hudson

This work considers a repeated principal-agent bandit game, where the principal can only interact with her environment through the agent. The principal and the agent have misaligned objectives and the choice of action is only left to the…

This paper studies algorithmic decision-making under human's strategic behavior, where a decision maker uses an algorithm to make decisions about human agents, and the latter with information about the algorithm may exert effort…

Computer Science and Game Theory · Computer Science 2024-09-16 Tian Xie , Xuwei Tan , Xueru Zhang

Reinforcement learners are agents that learn to pick actions that lead to high reward. Ideally, the value of a reinforcement learner's policy approaches optimality--where the optimal informed policy is the one which maximizes reward.…

Machine Learning · Computer Science 2021-05-27 Michael K. Cohen , Elliot Catt , Marcus Hutter

When developing reinforcement learning agents, the standard approach is to train an agent to converge to a fixed policy that is as close to optimal as possible for a single fixed reward function. If different agent behaviour is required in…

Multiagent Systems · Computer Science 2021-01-29 David O'Callaghan , Patrick Mannion
‹ Prev 1 2 3 10 Next ›