Vaibhav Jain

Vaibhav Jain

Master's student at Saarland University | HiWi at DFKI

Posts by Tags

AI

Improving RL using LLMs

3 minute read

Published:

Exploring different ways Large Language Models can help improve Reinforcement Learning through guidance, planning, reward shaping, and more.

BatchNorm

DSPy

Deep Learning

Experiments

LLMs

Improving RL using LLMs

3 minute read

Published:

Exploring different ways Large Language Models can help improve Reinforcement Learning through guidance, planning, reward shaping, and more.

OpenAI

PyTorch

Python

Rate Limits

agents

books

The paradox of choice

2 minute read

Published:

Barry Schwartz’s insights on how more choices can lead to less satisfaction - and my personal strategy for navigating choice overload

machine learning

Improving RL using LLMs

3 minute read

Published:

Exploring different ways Large Language Models can help improve Reinforcement Learning through guidance, planning, reward shaping, and more.

psychology

The paradox of choice

2 minute read

Published:

Barry Schwartz’s insights on how more choices can lead to less satisfaction - and my personal strategy for navigating choice overload

reinforcement learning

Improving RL using LLMs

3 minute read

Published:

Exploring different ways Large Language Models can help improve Reinforcement Learning through guidance, planning, reward shaping, and more.

review

The paradox of choice

2 minute read

Published:

Barry Schwartz’s insights on how more choices can lead to less satisfaction - and my personal strategy for navigating choice overload