Papers I Read Notes and Summaries

BabyAI - First Steps Towards Grounded Language Learning With a Human In the Loop

Introduction

  • BabyAI is a research platform to investigate and support the feasibility...


Poincaré Embeddings for Learning Hierarchical Representations

Introduction

  • Much of the work in representation leaning uses Euclidean vector spaces...


When Recurrent Models Don’t Need To Be Recurrent

Introduction

  • The paper explores “if a well behaved RNN can be replaced...


HoME - a Household Multimodal Environment

Introduction

  • Environment for learning using modalities like vision, audio, semantics, physics and...


Emergence of Grounded Compositional Language in Multi-Agent Populations

Introduction

  • The paper provides a multi-agent learning environment and proposes a learning...


A Semantic Loss Function for Deep Learning with Symbolic Knowledge

Introduction

  • The paper proposes an approach for using symbolic knowledge in deep...


Hierarchical Graph Representation Learning with Differentiable Pooling

Introduction

  • Most existing GNN (Graph Neural Network) methods are inherently flat and...


Imagination-Augmented Agents for Deep Reinforcement Learning

  • The paper presents I2A (Imagination Augmented Agent) that combines the model-based and model-free...


Kronecker Recurrent Units

Introduction

  • Recurrent Neural Networks have two key issues:

    • Over parameterization...


Learning Independent Causal Mechanisms

Introduction

  • The paper presents a very interesting approach for learning independent (inverse)...