Will Dabney

Research Scientist@Google·OpenReview

研究方向

deep reinforcement learning · distributional RL · natural language understanding · reinforcement learning · optimization · hierarchical reinforcement learning

7.8

Discovering Symbolic Cognitive Models from Human and Animal Behavior

ICML 2025Spotlight

7.6

Predictive Coding Enhances Meta-RL To Achieve Interpretable Bayes-Optimal Belief Representation Under Partial Observability

NeurIPS 2025Poster

三作

7.3

Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model

NeurIPS 2024Poster

通讯

5.8

A Distributional Analogue to the Successor Representation

ICLR 2024Rejected

5.8

Towards Perpetually Trainable Neural Networks

合作者 (20)

Will Dabney

Discovering Symbolic Cognitive Models from Human and Animal Behavior

Predictive Coding Enhances Meta-RL To Achieve Interpretable Bayes-Optimal Belief Representation Under Partial Observability

Plasticity as the Mirror of Empowerment

Uncertainty Prioritized Experience Replay

Normalization and effective learning rates in reinforcement learning

Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model

A Distributional Analogue to the Successor Representation

Towards Perpetually Trainable Neural Networks