Compositional RL Agents That Follow Language Commands in Temporal Logic

 Title Compositional RL Agents That Follow Language Commands in Temporal Logic Publication Type CBMM Memos Year of Publication 2021 Authors Kuo, Y-L, Barbu, A, Katz, B Abstract We demonstrate how a reinforcement learning agent can use compositional recurrent neural net- works to learn to carry out commands specified in linear temporal logic (LTL). Our approach takes as input an LTL formula, structures a deep network according to the parse of the formula, and determines satisfying actions. This compositional structure of the network enables zero-shot generalization to sig- nificantly more complex unseen formulas. We demonstrate this ability in multiple problem domains with both discrete and continuous state-action spaces. In a symbolic domain, the agent finds a sequence of letters that satisfy a specification. In a Minecraft-like environment, the agent finds a sequence of actions that conform to a formula. In the Fetch environment, the robot finds a sequence of arm config- urations that move blocks on a table to fulfill the commands. While most prior work can learn to execute one formula reliably, we develop a novel form of multi-task learning for RL agents that allows them to learn from a diverse set of tasks and generalize to a new set of diverse tasks without any additional training. The compositional structures presented here are not specific to LTL, thus opening the path to RL agents that perform zero-shot generalization in other compositional domains. DSpace@MIT https://hdl.handle.net/1721.1/141357