Projects

  • Continual Diffusion: Exploration and adaptation in non-stationary tasks using diffusion policies for reinforcement learning.

  • Game of Life: Fully parallelized Game of Life.

  • SchizoSpeak: An esolang created for schizophrenic programmers using TypeScript.

  • Alokhe: An English Pronunciation Discord Bot - Learn, Write, and Teach English with Transliteration.

  • MAP Inference in JAX: Revising existing code from Map-prop to JAX and scaling up to deeper networks, with supervision from Stephen Chung.

  • better_rl: A deep RL experimentation tool providing insights into state-visitation, replay buffers, and policy analysis.

Gunbir Singh Baveja. Last updated on Dec 2, 2025.