Papers I Read Notes and Summaries

Diversity is All You Need - Learning Skills without a Reward Function

Introduction

  • The paper proposes an approach to learn useful skills without a...


Modular meta-learning

Introduction

  • The paper proposes an approach for learning neural networks (modules) that...


Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies

Introduction

  • The paper proposes a simple and robust approach for hierarchically training...


Efficient Lifelong Learning with A-GEM

Contributions

  • A new (and more realistic) evaluation protocol for lifelong learning where...


Pre-training Graph Neural Networks with Kernels

Introduction

  • The paper proposes a pretraining technique that can be used with...


Smooth Loss Functions for Deep Top-k Classification

Introduction

  • For top-k classification tasks, cross entropy is widely used as the...


Hindsight Experience Replay

Introduction

  • Hindsight Experience Replay(HER) is a sample efficient technique to learn from...


Representation Tradeoffs for Hyperbolic Embeddings

Introduction

  • The paper describes a combinatorial approach to embed trees into hyperbolic...


Learned Optimizers that Scale and Generalize

Introduction

  • The paper introduces a learned gradient descent optimizer that has low...


One-shot Learning with Memory-Augmented Neural Networks

Introduction

  • The paper demonstrates that Memory Augmented Neural Networks (MANN) are suitable...