Object-oriented state editing for HRL
This addresses data efficiency issues in hierarchical reinforcement learning for AI agents, though it appears incremental with preliminary results.
The paper tackles the problem of improving data efficiency in hierarchical reinforcement learning by introducing agents that use object-oriented reasoning to consider alternate world states, achieving similar reward levels as non-hierarchical agents while being more data-efficient.
We introduce agents that use object-oriented reasoning to consider alternate states of the world in order to more quickly find solutions to problems. Specifically, a hierarchical controller directs a low-level agent to behave as if objects in the scene were added, deleted, or modified. The actions taken by the controller are defined over a graph-based representation of the scene, with actions corresponding to adding, deleting, or editing the nodes of a graph. We present preliminary results on three environments, demonstrating that our approach can achieve similar levels of reward as non-hierarchical agents, but with better data efficiency.