Hado Philip van Hasselt

发表

Insights in reinforcement rearning : formal analysis and empirical evaluation of temporal-difference learning algorithms

Hado Philip van Hasselt, Hado Philip van Hasselt, 2011 .

Introducing Symmetries to Black Box Meta Reinforcement Learning

Junhyuk Oh, Hado Philip van Hasselt, Louis Kirsch, 2021, AAAI.

L EARNING BY D IRECTIONAL G RADIENT D ESCENT

Ivo Danihelka, Matteo Hessel, Anirudh Goyal, 2022 .

Human-level Atari 200x faster

Adrià Puigdomènech Badia, C. Blundell, Hado Philip van Hasselt, 2022, ICLR.

Optimistic Meta-Gradients

Satinder Singh, Hado Philip van Hasselt, Brendan O'Donoghue, 2023, ArXiv.

Bootstrapped Meta-Learning

Satinder Singh, Hado Philip van Hasselt, Tom Zahavy, 2021, ICLR.

Reinforcement Learning in Continuous State and Action Spaces

Hado van Hasselt, Hado Philip van Hasselt, 2012, Reinforcement Learning.

Self-Consistent Models and Values pdf

Zita Marinho, David Silver, Matteo Hessel, 2021, NeurIPS.

Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration

Nan Rosemary Ke, Hado Philip van Hasselt, Chentian Jiang, 2023, ArXiv.

Emphatic Algorithms for Deep Reinforcement Learning

Matteo Hessel, Charles Blundell, Adam White, 2021, ICML.

Selective Credit Assignment

Doina Precup, Hado Philip van Hasselt, Diana Borsa, 2022, ArXiv.

Reinforcement Learning in Continuous Action Spaces

M.A. Wiering, H. van Hasselt, Hado van Hasselt, 2007, 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning.

Learning Expected Emphatic Traces for Deep RL pdf

Shangtong Zhang, Adam White, Ray Jiang, 2021, AAAI.

On the Convergence of Bounded Agents

Benjamin Van Roy, Doina Precup, Satinder Singh, 2023, ArXiv.

Two Novel On-policy Reinforcement Learning Algorithms based on TD(λ)-methods

M.A. Wiering, H. van Hasselt, M. Wiering, 2007, 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning.

Exploration via Epistemic Value Estimation

J. Shawe-Taylor, Simon Schmitt, Hado Philip van Hasselt, 2023, AAAI.

Chaining Value Functions for Off-Policy Learning

J. Shawe-Taylor, Simon Schmitt, Hado Philip van Hasselt, 2022, AAAI.