Shixiang Gu

A Divergence Minimization Perspective on Imitation Learning Methods

2019 · arXiv (Cornell University)

In many settings, it is desirable to learn decision-making and control policies through learning or bootstrapping from expert demonstrations. The most common approaches under this Imitation Learning (IL) framework are Behavioural Cloning (BC), and Inverse …

Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning

2021 · arXiv (Cornell University)

Progress in deep reinforcement learning (RL) research is largely enabled by benchmark task environments. However, analyzing the nature of those environments is often overlooked. In particular, we still do not have agreeable ways to measure …

Generalized Decision Transformer for Offline Hindsight Information Matching

2021 · arXiv (Cornell University)

How to extract as much learning signal from each trajectory data has been a key problem in reinforcement learning (RL), where sample inefficiency has posed serious challenges for practical applications. Recent works have shown that …

Large Language Models are Zero-Shot Reasoners

2022 · arXiv (Cornell University)

Pretrained large language models (LLMs) are widely used in many sub-fields of natural language processing (NLP) and generally known as excellent few-shot learners with task-specific exemplars. Notably, chain of thought (CoT) prompting, a recent technique …

Scaling Instruction-Finetuned Language Models

2022 · arXiv (Cornell University)

Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. In this paper we explore instruction finetuning with a particular focus on …