Related papers: The Behavioral Credibility Trilemma: When Calibrat…
In this work we provide provable regret guarantees for an online meta-learning control algorithm in an iterative control setting, where in each iteration the system to be controlled is a linear deterministic system that is different and…
Identifying controllable aspects of the environment has proven to be an extraordinary intrinsic motivator to reinforcement learning agents. Despite repeatedly achieving State-of-the-Art results, this approach has only been studied as a…
For the problem of task-agnostic reinforcement learning (RL), an agent first collects samples from an unknown environment without the supervision of reward signals, then is revealed with a reward and is asked to compute a corresponding…
With reinforcement learning, an agent could learn complex behaviors from high-level abstractions of the task. However, exploration and reward shaping remained challenging for existing methods, especially in scenarios where the extrinsic…
Self-evaluation is increasingly central to language model training, underpinning techniques from Constitutional AI to self-refinement. We investigate whether coupling self-evaluation to reward signals creates incentives for wireheading,…
We study the problem of learning-augmented predictive linear quadratic control. Our goal is to design a controller that balances \textit{"consistency"}, which measures the competitive ratio when predictions are accurate, and…
This paper addresses the challenge of offline policy learning in reinforcement learning with continuous action spaces when unmeasured confounders are present. While most existing research focuses on policy evaluation within partially…
Stochastic linear bandits are a fundamental model for sequential decision making, where an agent selects a vector-valued action and receives a noisy reward with expected value given by an unknown linear function. Although well studied in…
Despite the explosive growth of AI and the technologies built upon it, predicting and inferring the sub-optimal behavior of users or human collaborators remains a critical challenge. In many cases, such behaviors are not a result of…
One of the most natural approaches to reinforcement learning (RL) with function approximation is value iteration, which inductively generates approximations to the optimal value function by solving a sequence of regression problems. To…
Policy learning is a quickly growing area. As robotics and computers control day-to-day life, their error rate needs to be minimized and controlled. There are many policy learning methods and bandit methods with provable error rates that…
This position paper argues that behavioural assurance, even when carefully designed, is being asked to carry safety claims it cannot verify. AI governance frameworks enacted between 2019 and early 2026 require reviewable evidence of…
We examine online safe multi-agent reinforcement learning using constrained Markov games in which agents compete by maximizing their expected total rewards under a constraint on expected total utilities. Our focus is confined to an episodic…
As an important psychological and social experiment, the Iterated Prisoner's Dilemma (IPD) treats the choice to cooperate or defect as an atomic action. We propose to study the behaviors of online learning algorithms in the Iterated…
This paper presents a safe learning framework that employs an adaptive model learning algorithm together with barrier certificates for systems with possibly nonstationary agent dynamics. To extract the dynamic structure of the model, we use…
We prove that no continuous, utility-preserving wrapper defense-a function $D: X\to X$ that preprocesses inputs before the model sees them-can make all outputs strictly safe for a language model with connected prompt space, and we…
A solution to control for nonresponse bias consists of multiplying the design weights of respondents by the inverse of estimated response probabilities to compensate for the nonrespondents. Maximum likelihood and calibration are two…
Safety is a critical feature of controller design for physical systems. When designing control policies, several approaches to guarantee this aspect of autonomy have been proposed, such as robust controllers or control barrier functions.…
Autonomous robotic exploration has long attracted the attention of the robotics community and is a topic of high relevance. Deploying such systems in the real world, however, is still far from being a reality. In part, it can be attributed…
We propose and analyze a continuous-time robust reinforcement learning framework for optimal stopping under ambiguity. In this framework, an agent chooses a robust exploratory stopping time motivated by two objectives: robust…