Robot Navigation in Partially Observable Domains using Hierarchical Memory-Based Reinforcement Learning

 In this paper, we attempt to find a solution to the problem of robot navigation in a domain with partial observability. The domain is a grid-world with intersecting corridors, where the agent learns an optimal policy for navigation by making use of a hierarchical memory-based learning algorithm. We define a hierarchy of levels over which the agent abstracts the learning process, as well as its behaviour. The problem is modeled as a POMDP and a solution is obtained by implementing the SARSA algorithm, which incorporates Temporal Difference learning. The agent uses short-term memory and abstracts over minute details thereby enabling it to scale up to large partially observable domains.