Mahan's repositories
iLQG-MuJoCo
Iterative LQG for a couple of MuJoCo models
Model-Based-RL
Model-based Policy Gradients
UnsupervisedObjectDetection
Use your classification neural network for object detection and localization
Unity2OpenSim
Regenerate Movements of Unity w/ OpenSim
TrajOpt-KneedWalker
Finding a stable limit cycle for a passive kneed walker using trajectory optimization.
DeepAnaglyph3D
End-to-end generation of good old red-cyan 3D images via CNNs
LearnOpenGL
recently started to dabble in OpenGL
length-generalization
Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023
long-convs
long convolutions in jax
OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)
s4
Structured state space sequence models
sub-q-learning
break up the Q-function in linear parts which correspond to subrewards