https://github.com/raiszo/rl-agents

A collection of RL agents in tensorflow 2.0
https://github.com/raiszo/rl-agents

Last synced: 11 days ago
JSON representation

A collection of RL agents in tensorflow 2.0

• Host: GitHub
• URL: https://github.com/raiszo/rl-agents
• Owner: Raiszo
• License: mit
• Created: 2019-05-01T22:43:18.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2023-03-25T01:35:35.000Z (almost 2 years ago)
• Last Synced: 2024-03-15T08:04:37.854Z (11 months ago)
• Language: Jupyter Notebook
• Size: 409 KB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: README.org
  • License: LICENSE

Awesome Lists containing this project

README

        
#+TITLE: rl-agents

A collection of RL agents in tensorflow 2.0

* Usefull definitions

** PPO

   A good explanation of what this algorithm does is depicted in OpenAI's spinning up docs: "whose updates indirectly maximize performance, by instead maximizing a surrogate objective function which gives a conservative estimate for how much \(J(\pi_{\theta})\) will change as a result of the update"

** On-policy algorithms

   Each update only uses data colected while acting under the most recent version of the policy.

** Off-policy algorithms

   Each update can use data recorded at any point during trainning, regardless of how the agent was exploring the environment at that time.