Skip to content
View Rohan138's full-sized avatar

Block or report Rohan138

Report abuse

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

Report abuse
Rohan138/README.md

Biography

I am a Software Development Engineer at AMD, working on the ROCm for AI Models team. Previously, I studied Computer Engineering at Purdue University, interned at Anyscale across 2022 and 2023, and did research on multi-agent reinforcement learning under Dr. Jordan Terry of the Farama Foundation.

I'm passionate about language models and reinforcement learning, and am a contributor to several open-source reinforcement learning libraries, including OpenAI Gym, PettingZoo, and RLlib.

In my free time, I can be found climbing, playing squash, or at the piano.

Popular repositories Loading

  1. marl-baselines3 marl-baselines3 Public

    Multi-Agent Reinforcement Learning with Stable-Baselines3

    Python 20 2

  2. rllib-torch-maddpg rllib-torch-maddpg Public

    PyTorch implementation of MADDPG (Lowe et al.) in RLLib

    Python 9 3

  3. rt1-pytorch rt1-pytorch Public

    Forked from lucidrains/robotic-transformer-pytorch

    Implementation of RT1 (Robotic Transformer) in Pytorch

    Jupyter Notebook 3 1

  4. gym-algorithmic gym-algorithmic Public

    Python 2 3

  5. gym-legacy-toytext gym-legacy-toytext Public

    Python 1 2

  6. jos jos Public

    Forked from EE469/jos

    Main repo for JOS labs

    C 1