Implementation of some of the policy gradient methods in PyTorch.
-
Updated
Jul 27, 2022 - Python
Implementation of some of the policy gradient methods in PyTorch.
Deep reinforcement learning experiments
An RL agent using policy gradient to learn no-limit Texas hold'em.
simple and compact implementations of reinforcement learning benchmark algorithms
PyTorch Implementations of Standard Deep RL Algorithms (including REINFORCE, A2C, PPO)
Behaviour Cloning On OpenAI Environment
Implementation of REINFORCE for open ai env acrobot, epsilon greedy Q-Learning for open ai env taxi & TD(0) for custom gameshow env KBC.
Reinforce is a gradient-based Reinforcement Learning algorithm used for policy learning. It can be applied to both continuous and discrete environments.
My implementations of popular reinforcement learning methods based on other developers and research papers.
This notebook trains an agent to navigate a maze and reach a desired destination. It uses the Gym-MiniGrid's fourRoom-v0 environment as the maze. The agent is trained by using reiforcement learning's vanilla policy gradient (REINFORCE) algorithm.
Reinforcement Learning: Policy Gradient Methods
Bot averaging >60 apples on a 10x10 map with 2 apples on the map at a time
Simple, well-commented Pytorch implementations of REINFORCE and Actor Critic RL methods.
My reports for the reinforcement learning class given at the ENS
Add a description, image, and links to the reinforce topic page so that developers can more easily learn about it.
To associate your repository with the reinforce topic, visit your repo's landing page and select "manage topics."