Risto Miikkulainen and Lex Fridman discussing the importance of integration of Evolutionary Computation in Deep Networks in certain tasks such as: assessing interpretability to very deep architectures (layer depth, topology, etc.) based on the hyperparameter tuning.
-
Notifications
You must be signed in to change notification settings - Fork 2
parameter optimization of a reinforcement learning deep Q network with memory replay buffer using genetic algorithm in the snake game. base code for snake env from codecamp
License
roaked/snake-evolutionary-reinforcement-learning
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
parameter optimization of a reinforcement learning deep Q network with memory replay buffer using genetic algorithm in the snake game. base code for snake env from codecamp
Topics
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published