Reinforcement Learning in DeepSeek-R1
Details
** DeepSeek R1: Reinforcement Learning & AI Optimization Meetup**
Join us for an exciting discussion on DeepSeek R1, a cutting-edge reinforcement learning model that enhances reasoning and decision-making. We’ll explore advanced optimization techniques like Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO) and how they shape the future of AI.
We will analyze:
https://arxiv.org/pdf/2501.12948 and
https://www.youtube.com/watch?v=H20Hd6Xb7Qo
This event is focused on deep understanding difference of R1 and GPT architecture https://arxiv.org/pdf/2305.10435. Not contain practical workshop.
### What to expect?
✅ Insights into reinforcement learning
✅ Deep dive into PPO and GRPO optimization strategies
✅ Networking with AI enthusiasts, researchers, and developers
✅ A welcoming space for discussions and knowledge-sharing
### Event Details:
Date: April 27, 2025
⏰ Time: 1:00 AM (Duration: 2 hours)
Location: LendSpace, 4 Sherif Khimshiashvili St, Batumi, Georgia
Language: English
Entry: Free
Whether you're a beginner or an expert, come join us to explore the latest AI advancements and connect with like-minded individuals.
Reserve your spot and be part of the conversation!