Reinforcement Learning of Implicit and Explicit Control Flow in Instructions
This addresses the challenge of making reinforcement learning agents more adaptable to dynamic environments and complex instructions, though it is incremental as it builds on existing attention-based methods.
The paper tackled the problem of learning flexible control flow in reinforcement learning agents to handle both explicit (e.g., conditional branching) and implicit (e.g., due to stochastic dynamics) deviations from step-by-step instruction execution, achieving zero-shot generalization to longer novel instructions with performance surpassing baseline architectures in Minecraft- and StarCraft-inspired domains.
Learning to flexibly follow task instructions in dynamic environments poses interesting challenges for reinforcement learning agents. We focus here on the problem of learning control flow that deviates from a strict step-by-step execution of instructions -- that is, control flow that may skip forward over parts of the instructions or return backward to previously completed or skipped steps. Demand for such flexible control arises in two fundamental ways: explicitly when control is specified in the instructions themselves (such as conditional branching and looping) and implicitly when stochastic environment dynamics require re-completion of instructions whose effects have been perturbed, or opportunistic skipping of instructions whose effects are already present. We formulate an attention-based architecture that meets these challenges by learning, from task reward only, to flexibly attend to and condition behavior on an internal encoding of the instructions. We test the architecture's ability to learn both explicit and implicit control in two illustrative domains -- one inspired by Minecraft and the other by StarCraft -- and show that the architecture exhibits zero-shot generalization to novel instructions of length greater than those in a training set, at a performance level unmatched by two baseline recurrent architectures and one ablation architecture.