cfd_sureli adapted from Pytorch-RL-Agents
A few RL algorithms initially implemented by SuReLI with Pytorch and adapted to solve CFD cases
Algorithms
-
DDPG : Deep Deterministic Policy Gradient presented in Continuous control with deep reinforcement learning.
-
TD3 : Twin Delayed Deep Deterministic policy gradient Addressing Function Approximation Error in Actor-Critic Methods
-
SAC : Soft Actor-Critic presented in Soft Actor-Critic:Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
Requirements
- Python 3.7 or older versions
- torch, torchvision
- imageio
- gym
- matplotlib
- PyYAML
- numpy