All Posts

Published on
April 16, 2023
Potential-based Reward Shaping for Larger State Spaces
reinforcement-learning
Explore the use of potential-based rewards shaping to improve performance of RL algorithms for environments with larger state space.
Published on
April 30, 2022
Contrastive Learning in Distilled Models
deep-learning nlp
OMSCS Deep Learning Final project for Deep Learning course for Masters. Non peer reviewed. Application of contrastive learning on DistilBERT.
Published on
October 21, 2021
Using Double DQN to Land a Spaceship
deep-learning reinforcement-learning
Using Double DQN with soft updates to solve LunarLander-V2.

Potential-based Reward Shaping for Larger State Spaces