grid-world-rl
grid-world-rl copied to clipboard
Published
20 hours ago •
kevin-hanselman
kevin-hanselman
Value iteration, policy iteration, and Q-Learning in a grid-world MDP.
grid-world-rl
Implementations of MDP value iteration, MDP policy iteration, and Q-Learning in a toy grid-world setting.
TODO
The policy iteration implementation is suboptimal, as it does not use the closed-form solution. Pull requests are welcome.
Metadata
24
Stars
12
Forks
Watchers
Owner
kevin-hanselman
Metadata
Value iteration, policy iteration, and Q-Learning in a grid-world MDP.