Disaggregation Experiments
Experimental code for faster MDP solving and state abstraction discovery.
Experimental code used to study disaggregation techniques for faster Markov Decision Process solving and state abstraction discovery. The project connects approximate dynamic programming, projected Bellman operators, and abstract MDP constructions.
The experiments cover random MDPs and classical reinforcement-learning benchmarks such as Four Rooms, Mountain Car, Sutton’s racetrack, tandem queues, and hydro-valley management models.
Area: Markov Decision Processes, approximate dynamic programming, abstraction discovery.
Link: GitHub profile fallback.