Anca D. Dragan

UC Berkeley, CA, USA

21 papers at tracked venues · 18 at CORE A* · active 2024–2025

DBLP profile ↗ORCID 0000-0001-6312-5466 ↗Google Scholar ↗Homepage ↗

Venues

ICLR ×7 ICML ×6 NeurIPS ×4 ICRA ×2 AAAI ×1 AAMAS ×1

Frequent coauthors

Sergey Levine

×7

Stuart J. Russell

×5

Vivek Myers

×5

Cassidy Laidlaw

×3

Micah Carroll

×3

Joey Hong

×3

Justin Svegliato

×2

Mariah L. Schrum

×2

Evan Ellis

×2

Erdem Biyik

×2

Davis Foote

×2

Benjamin Eysenbach

×2

Papers

Adversaries Can Misuse Combinations of Safe Models
ICML 2025 ·
Erik Jones
, Anca D. Dragan,
Jacob Steinhardt
AssistanceZero: Scalably Solving Assistance Games
ICML 2025 ·
Cassidy Laidlaw
,
Eli Bronstein
,
Timothy Guo
,
Dylan Feng
,
Lukas Berglund
,
Justin Svegliato
,
Stuart Russell
, Anca D. Dragan
Context Steering: Controllable Personalization at Inference Time
ICLR 2025 ·
Jerry Zhi-Yang He
,
Sashrika Pandey
,
Mariah L. Schrum
, Anca D. Dragan
Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking
ICLR 2025 ·
Cassidy Laidlaw
,
Shivam Singhal
, Anca D. Dragan
On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback
ICLR 2025 ·
Marcus Williams
,
Micah Carroll
,
Adhyyan Narang
,
Constantin Weisser
,
Brendan Murphy
, Anca D. Dragan
Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL
NeurIPS 2025 ·
Joey Hong
, Anca D. Dragan,
Sergey Levine
Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning
ICLR 2025 ·
Joey Hong
, Anca D. Dragan,
Sergey Levine
Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following
NeurIPS 2025 ·
Vivek Myers
,
Bill Zheng
, Anca D. Dragan,
Kuan Fang
,
Sergey Levine
A Generalized Acquisition Function for Preference-based Reward Learning
ICRA 2024 ·
Evan Ellis
,
Gaurav R. Ghosal
,
Stuart J. Russell
, Anca D. Dragan,
Erdem Biyik
AI Alignment with Changing and Influenceable Reward Functions
ICML 2024 ·
Micah Carroll
,
Davis Foote
,
Anand Siththaranjan
,
Stuart Russell
, Anca D. Dragan
Confronting Reward Model Overoptimization with Constrained RLHF
ICLR 2024 ·
Ted Moskovitz
,
Aaditya K. Singh
,
DJ Strouse
,
Tuomas Sandholm
,
Ruslan Salakhutdinov
, Anca D. Dragan,
Stephen Marcus McAleer
Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation
ICML 2024 ·
Michelle Pan
,
Mariah L. Schrum
,
Vivek Myers
,
Erdem Biyik
, Anca D. Dragan
Defining Deception in Decision Making
AAMAS 2024 ·
Marwa Abdulhai
,
Micah Carroll
,
Justin Svegliato
, Anca D. Dragan,
Sergey Levine
Learning Optimal Advantage from Preferences and Mistaking It for Reward
AAAI 2024 ·
W. Bradley Knox
,
Stephane Hatgis-Kessell
,
Sigurdur O. Adalgeirsson
,
Serena Booth
, Anca D. Dragan,
Peter Stone
,
Scott Niekum
Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making
ICML 2024 ·
Vivek Myers
,
Chongyi Zheng
, Anca D. Dragan,
Sergey Levine
,
Benjamin Eysenbach
Learning to Assist Humans without Inferring Rewards
NeurIPS 2024 ·
Vivek Myers
,
Evan Ellis
,
Sergey Levine
,
Benjamin Eysenbach
, Anca D. Dragan
Learning to Model the World With Language
ICML 2024 ·
Jessy Lin
,
Yuqing Du
,
Olivia Watkins
,
Danijar Hafner
,
Pieter Abbeel
,
Dan Klein
, Anca D. Dragan
Offline RL with Observation Histories: Analyzing and Improving Sample Complexity
ICLR 2024 ·
Joey Hong
, Anca D. Dragan,
Sergey Levine
The Effective Horizon Explains Deep RL Performance in Stochastic Environments
ICLR 2024 ·
Cassidy Laidlaw
,
Banghua Zhu
,
Stuart Russell
, Anca D. Dragan
Toward Grounded Commonsense Reasoning
ICRA 2024 ·
Minae Kwon
,
Hengyuan Hu
,
Vivek Myers
,
Siddharth Karamcheti
, Anca D. Dragan,
Dorsa Sadigh
When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
NeurIPS 2024 ·
Leon Lang
,
Davis Foote
,
Stuart J. Russell
, Anca D. Dragan,
Erik Jenner
,
Scott Emmons