Itomigna2 / RL-algos-colab

Some RL algorithm implementation (PyTorch) (Colab executable)

Repository from Github https://github.comItomigna2/RL-algos-colab

a2c actor-critic colab deep-learning ppo reinforce reinforce-with-baseline reinforcement-learning-algorithms

RL-algos-colab

Policy gradient based RL algorithms

Implemented RL algorithms

REINFORCE
REINFORCE with baseline
One-step Actor Critic
Advantage Actor Critic (A2C)
Proximal Policy Optimization (PPO)

Links

CartPole-v1 env document : https://www.gymlibrary.dev/environments/classic_control/cart_pole/

Memo

This codes(.ipynb) are executable in Google Colab.

About

Some RL algorithm implementation (PyTorch) (Colab executable)

a2c actor-critic colab deep-learning ppo reinforce reinforce-with-baseline reinforcement-learning-algorithms

Languages

Language:Jupyter Notebook 100.0%