Code for A First-Occupancy Representation for Reinforcement Learning

dependencies: numpy, scipy, matplotlib, seaborn

files: 
- agents.py: basic agent classes for GPI, value iteration, the FR, and the SR
- envs.py: FourRoom and Escape environment classes
- frp.py: FR planning (FRP) agent class
- utils.py: basic helper functions
- runners.py: functions for running experiments
- four_rooms.ipynb: result notebook