Computationally Efficient Reinforcement Learning under Partial Observability
A key challenge in reinforcement learning is the inability of the agent to fully observe the latent state of the system. Partially observable Markov decision processes (POMDPs) are a generalization of Markov decision processes (MDPs) that model this challenge. Unfortunately, planning and learning ne...
Main Author: | |
---|---|
Other Authors: | |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2023
|
Online Access: | https://hdl.handle.net/1721.1/150191 |