Skip to content

Applying sevel reinforcement learning algorithms (Q-Learning (with NN as Q-values approximator), modified reward Q-Learning, Double Deep Q-Learning, Dueling Deep Q-Learning) to OpenAI gym's Acrobot environment and compare their performance.

Notifications You must be signed in to change notification settings

PongC/AcrobotRL

Repository files navigation

AcrobotRL

Applying sevel reinforcement learning algorithms (Q-Learning (with NN as Q-values approximator), modified reward Q-Learning, Double Deep Q-Learning, Dueling Deep Q-Learning) to OpenAI gym's Acrobot environment and compare their performance.

About

Applying sevel reinforcement learning algorithms (Q-Learning (with NN as Q-values approximator), modified reward Q-Learning, Double Deep Q-Learning, Dueling Deep Q-Learning) to OpenAI gym's Acrobot environment and compare their performance.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published