Projects in Awesome Lists tagged with kfac
A curated list of projects in awesome lists tagged with kfac .
https://github.com/ikostrikov/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).
a2c acktr actor-critic advantage-actor-critic ale atari continuous-control deep-learning deep-reinforcement-learning hessian kfac kronecker-factored-approximation mujoco natural-gradients ppo proximal-policy-optimization pytorch reinforcement-learning roboschool second-order
Last synced: 13 Apr 2025
https://github.com/tfjgeorge/nngeometry
{KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch
ek-fac ekfac fim fisher-information-matrix gram hessian jacobian k-fac kfac neural-tangent-kernel ntk pytorch tangent
Last synced: 16 May 2025
https://github.com/f-dangel/einconv
Convolutions and more as einsum for PyTorch
convolution einsum einsum-notation fisher ggn im2col jvp kfac ntk pytorch tensornetwork transpose-convolution vjp
Last synced: 04 Sep 2025
https://github.com/yorkerlin/structuredngd-dl
Matrix-multiplication-only KFAC; Code for ICML 2023 paper on Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning
deep-learning fisher hessian-free kfac natural-gradients optimization-methods optimizer pytorch-implementation second-order-optimization
Last synced: 11 Oct 2025
https://github.com/saif99j/gail
🌊 Implement advanced algorithms for USV path planning using reinforcement and imitation learning, ensuring efficient and safe navigation in complex environments.
actor-critic advantage-actor-critic biped continuous-control deep-reinforcement-learning gail generative-adversarial-network imitation-learning inverse-reinforcement-learning irl kfac kronecker-factored-approximation openai-gym pytorch roboschool tensorflow trpo vail
Last synced: 18 Apr 2026
