ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Anca Dragan

Anca Dragan

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 12:57 AM AMS

19

papers

581

total citations

papers (19)

Reward-rational (implicit) choice: A unifying formalism for reward learning

NEURIPS 2020arXiv

Learning to Model the World With Language

AI Alignment with Changing and Influenceable Reward Functions

On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback

AvE: Assistance via Empowerment

NEURIPS 2020arXiv

Bridging RL Theory and Practice with the Effective Horizon

NEURIPS 2023arXiv

Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making

Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking

Learning Optimal Advantage from Preferences and Mistaking It for Reward

First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization

NEURIPS 2022arXiv

Preference learning along multiple criteria: A game-theoretic perspective

NEURIPS 2020arXiv

Context Steering: Controllable Personalization at Inference Time

Pragmatic Image Compression for Human-in-the-Loop Decision-Making

NEURIPS 2021arXiv

Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning

The Effective Horizon Explains Deep RL Performance in Stochastic Environments

AssistanceZero: Scalably Solving Assistance Games

Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation

Learning to Influence Human Behavior with Offline Reinforcement Learning

NEURIPS 2023arXiv

Uni[MASK]: Unified Inference in Sequential Decision Problems