Aaron Havens's repositories
structure_learning
Implementation of k2 structure learning for bayesian nets.
FlowMatching
A repo where I play with conditional flow approaches for learning time-varying vector-fields.
ExploitingLipschitzDEQ
Supplementary codes for the Neurips 2023 paper: Exploiting Connections between Lipschitz Structures for Certifiably Robust Deep Equilibrium Models
alpha-beta-depth-cutoff
Reversie/Othello alpha-beta game playing agent
baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
binomialDist
Toy binomial distributions and experiements
chainer
A flexible framework of neural networks for deep learning
Chainer_MLAH
More portable version of prevous multi-task algo MLAH
CS472
Where I keep all of my Artificial Intelligence junk
Forced-Variational-Integrator-Networks
deep soft arm mpc
gym
A toolkit for developing and comparing reinforcement learning algorithms.
HavensHashing
Implementation of generically typed hashmap using linear probing
LoFAST
Coming soon
NBA-Player-Movements
🏀 Visualization of NBA games from raw SportVU data logs
neural_lander_sim_1d
A simple 1d simulator for the "Neural-Lander" paper, ICRA 2019
nonlinear-induced-gains
python implementation of a power-iteration method for computing the L2 induced gain of a nonlinear system.
Reinforcement-Learning
Reinforcement learning off-policy for small and large MDPs.
stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
vision-transformers-cifar10
Modify for orthogonal training