Akbir Khan's repositories
akbir.github.io
Personal Website
ray_tracer
Ray-tracer written in go
bag-of-poses
Bag of words approach with OpenPose for categorising group body language.
Bag-of-Visual-Words-Python
Implementing Bag of Visual words approach for object classification and detection
chip_8_rust
Chip 8 Emulator
debate-1
Debate interface, experiments, etc.
deq-jax_test
Testing Module for deq-jax
gpt-3
GPT-3: Language Models are Few-Shot Learners
dotfiles
Easily deploy my zsh and tmux configuration on new machines. Includes local and remote aliases to improve workflow.
gymnax
RL Environments in JAX 🌍
human_aware_rl
Code for "On the Utility of Learning about Humans for Human-AI Coordination"
jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
linear-regression
Example of Python WebApp for machine learning classifier.
magi
Reinforcement learning library in JAX.
megastep
megastep helps you build 1-million FPS reinforcement learning environments on a single GPU
overcooked_ai
A benchmark environment for fully cooperative human-AI performance.
POCA
Dataset to accompany ACL submission
POLA
For Baseline Comparison
pytorch-a2c-ppo-acktr-gail
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
remarkable-arxiv
Download+Crop+Send arxiv papers to remarkable in one click
rl-jax
Messing around with RL agents in Jax
sequential_social_dilemma_games
Repo for reproduction of sequential social dilemmas
stable-baselines
A fork of OpenAI Baselines, implementations of reinforcement learning algorithms