Reducing the Planning Horizon Through Reinforcement Learning

Planning is a computationally expensive process, which can limit the reactivity of autonomous agents. Planning problems are usually solved in isolation, independently of similar, previously solved problems. The depth of search that a planner requires to find a solution, known as the planning horizon, is a critical factor when integrating planners into reactive agents. We consider the case of an agent repeatedly carrying out a task from different initial states. We propose a combination of classical planning and model-free reinforcement learning to reduce the planning horizon over time. Control is smoothly transferred from the planner to the model-free policy as the agent compiles the planner's policy into a value function. Local exploration of the model-free policy allows the agent to adapt to the environment and eventually overcome model inaccuracies. We evaluate the efficacy of our framework on symbolic PDDL domains and a stochastic grid world environment and show that we are able to significantly reduce the planning horizon while improving upon model inaccuracies.

Automated summary

Planning is computationally expensive and limits the reactivity of autonomous agents. We propose a combination of classical planning and model-free reinforcement learning to reduce the planning horizon and adapt to the environment. Our framework has been evaluated on symbolic PDDL domains and a stochastic grid world environment, showing significant reduction in planning horizon and improved performance.