1mgofficial

Image from unsplash

In the previous article, we discussed two methods under model-free RL algorithms: policy-based and value-based. This article will focus on policy-based algorithms such as REINFORCE, Actor-Critic, and PPO methods of learning, and also implement the algorithms using simple Cart-Pole example.

Policy Gradient:

Exploring the promise, pitfalls, and practical applications of using LLMs to automate AI evaluation - from synthetic QA to clinical reasoning tasks.

In this article, we will go through the basics of reinforcement learning focusing on the framework of RL, some of the key concepts like Markov Decision Process, and Bellman Equations which forms the mathematical foundation of RL. We will also see different RL algorithms and the challenges that we face in RL.

What is Reinforcement Learning?

One Reward to Rule Them All — Inside the Engine Powering Homepage Recommendation

Co-author’s:

1. Pankaj Pandey (Senior Technical Architect @ Tata 1mg)
2. Prashant Mishra (Technical Architect @ Tata 1mg)
3. Vimal Sharma (Technical Architect @ Tata 1mg)

Scalable task scheduling — Server-Less

Co-Authors: Pankaj Pandey, Prashant Mishra, Aman Garg

Introduction

Dopamine — Tata 1mg’s design system

Co-author’s:

1. Prashant Mishra (Technical Architect @ Tata 1mg)
2. Sankar Yadalam (Technical Architect @ Tata 1mg)
3. Aman Garg (Associate Technical Architect @ Tata 1mg)
4. Dollar Dhingra (Associate Engineering Manager @ Tata 1mg)

Introduction

Co-authors:

1. Swati Grover ( Associate Technical Architect @ Tata 1mg)
2. Prashant Mishra (Technical Architect @ Tata 1mg)

*Introduction

Bringing about a paradigm shift in development & deployment

Co-author’s:

1. Prashant Mishra (Technical Architect @ Tata 1mg)
2. Vimal Sharma (Technical Architect @ Tata 1mg)
3. Aman Garg (Associate Technical Architect @ Tata 1mg)

Introduction