Papers I Read Notes and Summaries

Large Memory Layers with Product Keys

22 Aug 2019

Introduction

  • The paper proposes a structured key-value memory layer that:
    • Can scale...

Abductive Commonsense Reasoning

15 Aug 2019

Introduction

  • The paper presents the task of abductive NLP (pronounced as alpha...

Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models

08 Aug 2019

Introduction

  • The paper proposes a new algorithm called as Probabilistic Ensemble with...

Assessing Generalization in Deep Reinforcement Learning

01 Aug 2019

  • The paper presents a benchmark and experimental protocol (environments, metrics, baselines, training/testing setup)...

Quantifying Generalization in Reinforcement Learning

25 Jul 2019

Introduction

  • The paper introduces a new, procedurally generated environment called as CoinRun...

Set Transformer - A Framework for Attention-based Permutation-Invariant Neural Networks

18 Jul 2019

Introduction

  • Consider problems where the input to the model is a set....

Measuring abstract reasoning in neural networks

27 Jun 2019

Introduction

  • The paper proposes a dataset to diagnose the abstract reasoning capabilities...

Hamiltonian Neural Networks

20 Jun 2019

Introduction

  • The paper proposes a very cool idea at the intersection of...

Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations

13 Jun 2019

Introduction

  • The paper proposes a new inverse RL (IRL) algorithm, called as...

Meta-Reinforcement Learning of Structured Exploration Strategies

08 Jun 2019

Introduction

  • The paper looks at the problem of learning structured exploration policies...