 Would I have gotten that reward? Long-term credit assignment by
counterfactual contribution analysisNeural Information Processing Systems (NeurIPS), 2023 |
 Free Will Belief as a consequence of Model-based Reinforcement LearningArtificial General Intelligence (AGI), 2021 |
 Self-Consistent Models and ValuesNeural Information Processing Systems (NeurIPS), 2021 |
 Policy Gradients Incorporating the FutureInternational Conference on Learning Representations (ICLR), 2021 |
 Muesli: Combining Improvements in Policy OptimizationInternational Conference on Machine Learning (ICML), 2021 Matteo Hessel Ivo Danihelka Fabio Viola A. Guez Simon Schmitt Laurent Sifre T. Weber David Silver H. V. Hasselt |
 Counterfactual Credit Assignment in Model-Free Reinforcement LearningInternational Conference on Machine Learning (ICML), 2020 |
