MS in Computer Science @ University of Massachusetts Amherst
I work at the intersection of reinforcement learning and deep learning, with a focus on building agents that learn efficiently, stay stable, and generalize to real-world problems.
- AltNet -- Accepted at AAMAS 2026. A dual-network architecture that solves the plasticity-stability dilemma in deep RL by alternating active and passive networks during periodic resets. Outperforms SAC, Standard Resets, and RDE across DeepMind Control Suite benchmarks. [Paper] [Code]
| Project | Description | Tech |
|---|---|---|
| AltNet | Addressing the plasticity-stability dilemma in RL (AAMAS 2026) | Python, PyTorch, Stable-Baselines3, DMC |
| Recommendation with Transformers | Personalized movie recommendations using the Transformer architecture on MovieLens 1M | Python, PyTorch |
| RL for Stock Trading | Comparing A2C, DDPG for automated multi-stock portfolio trading | Python, PyTorch |