Pinned Repositories
akbir
akbir.github.io
Personal Website
anthill-backend
ARENA_3.0
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
deq-jax
[NeurIPS'19] Deep Equilibrium Models Jax Implementation
ray_tracer
Ray-tracer written in go
jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
akbir's Repositories
akbir/deq-jax
[NeurIPS'19] Deep Equilibrium Models Jax Implementation
akbir/akbir.github.io
Personal Website
akbir/ray_tracer
Ray-tracer written in go
akbir/akbir
akbir/anthill-backend
akbir/ARENA_3.0
akbir/bag-of-poses
Bag of words approach with OpenPose for categorising group body language.
akbir/Bag-of-Visual-Words-Python
Implementing Bag of Visual words approach for object classification and detection
akbir/chip_8_rust
Chip 8 Emulator
akbir/debate-1
Debate interface, experiments, etc.
akbir/deq-jax_test
Testing Module for deq-jax
akbir/gpt-3
GPT-3: Language Models are Few-Shot Learners
akbir/dotfiles
Easily deploy my zsh and tmux configuration on new machines. Includes local and remote aliases to improve workflow.
akbir/gymnax
RL Environments in JAX 🌍
akbir/human_aware_rl
Code for "On the Utility of Learning about Humans for Human-AI Coordination"
akbir/jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
akbir/linear-regression
Example of Python WebApp for machine learning classifier.
akbir/magi
Reinforcement learning library in JAX.
akbir/megastep
megastep helps you build 1-million FPS reinforcement learning environments on a single GPU
akbir/overcooked_ai
A benchmark environment for fully cooperative human-AI performance.
akbir/POCA
Dataset to accompany ACL submission
akbir/POLA
For Baseline Comparison
akbir/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).
akbir/remarkable-arxiv
Download+Crop+Send arxiv papers to remarkable in one click
akbir/rl-jax
Messing around with RL agents in Jax
akbir/sequential_social_dilemma_games
Repo for reproduction of sequential social dilemmas
akbir/stable-baselines
A fork of OpenAI Baselines, implementations of reinforcement learning algorithms