Kaushik Rajan – Medium

Kaushik Rajan

Pinned

Published in
TDS Archive

Advancing AI Reasoning: Meta-CoT and System 2 Thinking

How Meta-CoT enhances system 2 reasoning for complex AI challenges

Jan 20

Advancing AI Reasoning: Meta-CoT and System 2 Thinking

Jan 20

Pinned

Published in
Generative AI

COCONUT: Redefining Reasoning in Large Language Models

Revolutionizing reasoning in large language models through latent space.

Dec 17, 2024

COCONUT: Redefining Reasoning in Large Language Models

Dec 17, 2024

Pinned

Published in
AI Advances

Neural Fictitious Self-Play (NFSP) for Imperfect-Information Games

How AI Advances Decision-Making in Complex Games Without Domain Expertise

Dec 26, 2024

Neural Fictitious Self-Play (NFSP) for Imperfect-Information Games

Dec 26, 2024

Pinned

Published in
AI Advances

Learning by Doing: An Introduction to Reinforcement Learning

How AI Agents Acquire Knowledge Through Trial and Error

Dec 14, 2024

Learning by Doing: An Introduction to Reinforcement Learning

Dec 14, 2024

Published in
Data Science Collective

From Pixels to Skill: Understanding AI through Mario’s Reinforcement Learning Adventures

Readers who are not Medium members are welcome to read this article via this link.

4d ago

From Pixels to Skill: Understanding AI through Mario’s Reinforcement Learning Adventures

4d ago

Published in
Generative AI

Pixels, Prompts, and Ponyo

The technology behind the viral Ghibli trend

6d ago

Pixels, Prompts, and Ponyo

6d ago

Published in
Towards AI

How I Built an Adaptive Concept Explainer Using Hugging Face Models

Demystifying Complex Ideas Through Multi-Level Explanations

6d ago

How I Built an Adaptive Concept Explainer Using Hugging Face Models

6d ago

Mastering the Reward Loop: A Hands-On Guide to Reinforcement Learning with Python

From zero to agent: building intelligent systems that learn through experience

Mar 3

Mastering the Reward Loop: A Hands-On Guide to Reinforcement Learning with Python

Mar 3

Magma: Building Multimodal AI Agents with Action Grounding

Implementing a foundation model that bridges understanding and action across digital and physical environments

Feb 28

Magma: Building Multimodal AI Agents with Action Grounding

Feb 28

Published in
AI Advances

Reinforcement Learning in Competitive Programming

How Chain-of-Thought Powers AI Code Solutions

Feb 17

Reinforcement Learning in Competitive Programming

Feb 17

Kaushik Rajan

Kaushik Rajan

Friend of Medium

Applied scientist and researcher with a decade of experience (4 yrs at Amazon). Masters in CS. Research interests: Deep RL, Game Theory, Decision Science.

Following

Help
Status
About
Careers
Press
Blog
Privacy
Rules
Terms
Text to speech