Contributions:3 releases, 178 pushes, 5 tags in 2 years 8 months
This project solves the classical grid world problem first with DP methods of RL like Policy Iteration and Value Iteration. Q learning is implemented too. Q learning is then implemented with changing positions of obstacles in the grid.
Contributions:14 commits, 2 PRs, 13 pushes in 2 years 9 months
grid-worldq-learningvalue-iteration