4 results found Sort:

ikostrikov
pytorch-a2c-ppo-acktr-gail ikostrikov
829
3.6k
mit
67
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) ...
a2c ale ppo kfac acktr atari mujoco hessian pytorch roboschool actor-critic second-order deep-learning natural-gradients continuous-control advantage-actor-critic reinforcement-learning deep-reinforcement-learning proximal-policy-optimization kronecker-factored-approximation
Created 2017-08-22
274 commits to master branch, last one 2 years ago
tfjgeorge
nngeometry tfjgeorge
20
206
mit
7
{KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch
fim ntk gram kfac ekfac k-fac ek-fac pytorch tangent jacobian neural-tangent-kernel fisher-information-matrix
Created 2019-09-12
451 commits to master branch, last one about a month ago
gpauloski
kfac-pytorch gpauloski
25
75
mit
4
Distributed K-FAC Preconditioner for PyTorch
kfac pytorch optimizer distributed deep-learning second-order-optimization
Created 2020-02-16
614 commits to main branch, last one 4 days ago
MaximeRobeyns
bayesian_lora MaximeRobeyns
1
25
apache-2.0
4
Bayesian Low-Rank Adaptation for Large Language Models
llm kfac laplace-approximation
Created 2024-01-19
41 commits to master branch, last one 3 months ago