Implementing the two pioneering IRL papers "Algorithms for Inverse Reinforcement Learning" - (Ng &Russell 2000) and "Maximum Entropy Inverse Reinforcement Learning" - (Ziebart et al. 2008)
Implement the paper "Algorithms for Inverse Reinforcement Learning" - (Ng & Russell 2000) and replicate results for,
- Finite State Space: Gridworld
- Large State Space: Mountain Car
- Through Sampled Trajectories: Continuous Gridworld
Implement the paper "Maximum Entropy Inverse Reinforcement Learning" - (Ziebart et al. 2008) and replicate results for,
- Simple Gridworld
- 2-D Maze
