PPaperPicks

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

Frequent coauthors

Cassidy Laidlaw
DBLP profile ↗ORCID search ↗
×3
Joey Hong
DBLP profile ↗ORCID search ↗
×3
Vivek Myers
DBLP profile ↗ORCID search ↗
×3
Erik Jones
DBLP profile ↗ORCID search ↗
×1
Jerry Zhi-Yang He
DBLP profile ↗ORCID search ↗
×1
Marcus Williams
DBLP profile ↗ORCID search ↗
×1
Evan Ellis
DBLP profile ↗ORCID search ↗
×1
Micah Carroll
DBLP profile ↗ORCID search ↗
×1
Ted Moskovitz
DBLP profile ↗ORCID search ↗
×1
Michelle Pan
DBLP profile ↗ORCID search ↗
×1
Marwa Abdulhai
DBLP profile ↗ORCID search ↗
×1
W. Bradley Knox
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Adversaries Can Misuse Combinations of Safe Models
    ICML 2025 ·
    Erik Jones
    DBLP profile ↗ORCID search ↗
  2. AssistanceZero: Scalably Solving Assistance Games
    ICML 2025 ·
    Cassidy Laidlaw
    DBLP profile ↗ORCID search ↗
  3. Context Steering: Controllable Personalization at Inference Time
    ICLR 2025 ·
    Jerry Zhi-Yang He
    DBLP profile ↗ORCID search ↗
  4. Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking
    ICLR 2025 ·
    Cassidy Laidlaw
    DBLP profile ↗ORCID search ↗
  5. On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback
    ICLR 2025 ·
    Marcus Williams
    DBLP profile ↗ORCID search ↗
  6. Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL
    NeurIPS 2025 ·
    Joey Hong
    DBLP profile ↗ORCID search ↗
  7. Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning
    ICLR 2025 ·
    Joey Hong
    DBLP profile ↗ORCID search ↗
  8. Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following
    NeurIPS 2025 ·
    Vivek Myers
    DBLP profile ↗ORCID search ↗
  9. A Generalized Acquisition Function for Preference-based Reward Learning
    ICRA 2024 ·
    Evan Ellis
    DBLP profile ↗ORCID search ↗
  10. AI Alignment with Changing and Influenceable Reward Functions
    ICML 2024 ·
    Micah Carroll
    DBLP profile ↗ORCID search ↗
  11. Confronting Reward Model Overoptimization with Constrained RLHF
    ICLR 2024 ·
    Ted Moskovitz
    DBLP profile ↗ORCID search ↗
  12. Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation
    ICML 2024 ·
    Michelle Pan
    DBLP profile ↗ORCID search ↗
  13. Defining Deception in Decision Making
    AAMAS 2024 ·
    Marwa Abdulhai
    DBLP profile ↗ORCID search ↗
  14. Learning Optimal Advantage from Preferences and Mistaking It for Reward
    AAAI 2024 ·
    W. Bradley Knox
    DBLP profile ↗ORCID search ↗
  15. Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making
    ICML 2024 ·
    Vivek Myers
    DBLP profile ↗ORCID search ↗
  16. Learning to Assist Humans without Inferring Rewards
    NeurIPS 2024 ·
    Vivek Myers
    DBLP profile ↗ORCID search ↗
  17. Learning to Model the World With Language
    ICML 2024 ·
    Jessy Lin
    DBLP profile ↗ORCID search ↗
  18. Offline RL with Observation Histories: Analyzing and Improving Sample Complexity
    ICLR 2024 ·
    Joey Hong
    DBLP profile ↗ORCID search ↗
  19. The Effective Horizon Explains Deep RL Performance in Stochastic Environments
    ICLR 2024 ·
    Cassidy Laidlaw
    DBLP profile ↗ORCID search ↗
  20. Toward Grounded Commonsense Reasoning
    ICRA 2024 ·
    Minae Kwon
    DBLP profile ↗ORCID search ↗
  21. When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
    NeurIPS 2024 ·
    Leon Lang
    DBLP profile ↗ORCID search ↗