Related papers: Auditable Decision Models with Learned Abstention …
Traditional approaches in offline reinforcement learning aim to learn the optimal policy that maximizes the cumulative reward, also known as return. It is increasingly important to adjust the performance of AI agents to meet human…
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…
The Decision Transformer (DT) has established a powerful sequence modeling approach to offline reinforcement learning. It conditions its action predictions on Return-to-Go (RTG), using it both to distinguish trajectory quality during…
Automated decision systems (ADS) are broadly deployed to inform and support human decision-making across a wide range of consequential settings. However, various context-specific details complicate the goal of establishing meaningful…
Deep neural networks are behind many of the recent successes in machine learning applications. However, these models can produce overconfident decisions while encountering out-of-distribution (OOD) examples or making a wrong prediction.…
Predictive algorithms inform consequential decisions in settings with selective labels: outcomes are observed only for units selected by past decision makers. This creates an identification problem under unobserved confounding -- when…
Motion prediction and cost evaluation are vital components in the decision-making system of autonomous vehicles. However, existing methods often ignore the importance of cost learning and treat them as separate modules. In this study, we…
We propose a novel adaptive reinforcement learning control approach for fault tolerant control of degrading systems that is not preceded by a fault detection and diagnosis step. Therefore, \textit{a priori} knowledge of faults that may…
Most known regret bounds for reinforcement learning are either episodic or assume an environment without traps. We derive a regret bound without making either assumption, by allowing the algorithm to occasionally delegate an action to an…
While controllable Text-to-Speech (TTS) has achieved notable progress, most existing methods remain limited to inter-utterance-level control, making fine-grained intra-utterance expression challenging due to their reliance on non-public…
We consider the problem of online learning in Linear Quadratic Control systems whose state transition and state-action transition matrices $A$ and $B$ may be initially unknown. We devise an online learning algorithm and provide guarantees…
Clinical AI systems frequently suffer performance decay post-deployment due to temporal data shifts, such as evolving populations, diagnostic coding updates (e.g., ICD-9 to ICD-10), and systemic shocks like the COVID-19 pandemic. Addressing…
We propose the use of Bayesian networks, which provide both a mean value and an uncertainty estimate as output, to enhance the safety of learned control policies under circumstances in which a test-time input differs significantly from the…
As artificial agents become increasingly capable, what internal structure is *necessary* for an agent to act competently under uncertainty? Classical results show that optimal control can be *implemented* using belief states or world…
The specification and validation of robotics applications require bridging the gap between formulating requirements and systematic testing. This often involves manual and error-prone tasks that become more complex as requirements, design,…
Optimal control of complex environments with robotic systems faces two complementary and intertwined challenges: efficient organization of sensory state information and far-sighted action planning. Because the reinforcement learning…
Human decision-making is strongly influenced by cognitive biases, particularly under conditions of uncertainty and risk. While prior work has examined bias in single-step decisions with immediate outcomes and in human interaction with a…
With the increasing availability of open-source robotic data, imitation learning has become a promising approach for both manipulation and locomotion. Diffusion models are now widely used to train large, generalized policies that predict…
This paper presents a deep learning based model predictive control algorithm for control affine nonlinear discrete time systems with matched and bounded state-dependent uncertainties of unknown structure. Since the structure of…
Sequential prediction problems such as imitation learning, where future observations depend on previous predictions (actions), violate the common i.i.d. assumptions made in statistical learning. This leads to poor performance in theory and…