Doina Precup
~Doina_Precup1
24
论文总数
12.0
年均投稿
平均评分
接收情况18/24
会议分布
ICLR
12
NeurIPS
9
COLM
2
ICML
1
发表论文 (24 篇)
202515 篇
4
Identifying and Addressing Delusions for Target-Directed Decision Making
ICLR 2025Rejected
5
Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks
NeurIPS 2025Poster
4
Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning
ICLR 2025Poster
4
Learning subgoal representations from state graphs in goal-conditioned hierarchical reinforcement learning
ICLR 2025withdrawn
5
Interpreting neural networks depends on the level of abstraction: Revisiting modular addition
ICLR 2025Rejected
4
Long-Term Fairness in Reinforcement Learning with Bisimulation Metrics
ICLR 2025Rejected
3
Selective Unlearning via Representation Erasure Using Domain Adversarial Training
ICLR 2025Poster
3
Rejecting Hallucinated State Targets during Planning
ICML 2025Poster
4
Language Agents Mirror Human Causal Reasoning Biases. How Can We Help Them Think Like Scientists?
COLM 2025Poster
3
Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts
COLM 2025Poster
4
MaestroMotif: Skill Design from Artificial Intelligence Feedback
ICLR 2025Oral
4
Capturing Individual Human Preferences with Reward Features
NeurIPS 2025Poster
4
EnzymeFlow: Generating Reaction-specific Enzyme Catalytic Pockets through Flow Matching and Co-Evolutionary Dynamics
ICLR 2025Rejected
4
Plasticity as the Mirror of Empowerment
NeurIPS 2025Spotlight
4
Training Language Models to Self-Correct via Reinforcement Learning
ICLR 2025Oral
20249 篇
3
Option Boosting
ICLR 2024Rejected
3
Adaptive Exploration for Data-Efficient General Value Function Evaluations
NeurIPS 2024Poster
3
Parseval Regularization for Continual Reinforcement Learning
NeurIPS 2024Poster
3
QGFN: Controllable Greediness with Action Values
NeurIPS 2024Poster
4
Learning Successor Features the Simple Way
NeurIPS 2024Poster
4
Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning
ICLR 2024Poster
3
Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo
ICLR 2024Poster
3
Efficient Reinforcement Learning by Discovering Neural Pathways
NeurIPS 2024Poster
4
Offline Multitask Representation Learning for Reinforcement Learning
NeurIPS 2024Poster