vijusudhi/ppo-LunarLander-v2
Reinforcement Learning
•
Updated
•
4
Viju Sudhi
vijusudhi
AI & ML interests
- LLM optimization / model compression techniques, including quantization, pruning and knowledge distillation
- (Generative) Information Retrieval
- Model-agnostic explainability techniques
- Hallucination mitigation
Organizations
