Introduction

• Training models with large minibatches (using distributed synchronous SGD) can lead...
  

Introduction

• The paper proposes a technique (called Parameter Superposition or PSP) for...
  

Introduction

• The paper studies five different techniques for stat abstraction in MDPs...
  

Introduction

• The paper proposes parameter-reduction techniques to lower the memory consumption (and...
  

Introduction

• Procedural text comprehension tasks focus on modeling the effect of actions...
  

Introduction

• The paper presents the MuZero algorithm that performs planning with a...
  

Introduction

• The paper introduces Contrastively-trained Structured World Models (C-SWMs).

• These...
  

• Link to the paper

• The paper considers the task of...
  

Introduction

• The paper proposes MAML++ - a modification of MAML algorithm that...
  

Introduction

• The paper proposes the PHYRE (PHYsical REasoning) benchmark - consisting of...