Thanks to visit codestin.com
Credit goes to github.com

Skip to content
View mansi99000's full-sized avatar

Block or report mansi99000

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
mansi99000/README.md

Hi, I'm Mansi Maheshwari

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.


Research

  • 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]

Featured Projects

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

Connect

Pinned Loading

  1. mansi99000 mansi99000 Public