LTL2Action: Generalizing LTL Instructions for Multi-Task RL
This addresses the challenge of enabling RL agents to handle diverse, temporally extended instructions in multi-task settings, representing an incremental advance in instruction-following RL.
The paper tackles the problem of teaching deep reinforcement learning agents to follow complex instructions expressed in linear temporal logic (LTL) for multi-task environments, achieving generalization to unseen tasks with experiments on combinatorial sets of up to ~10^39 unique tasks.
We address the problem of teaching a deep reinforcement learning (RL) agent to follow instructions in multi-task environments. Instructions are expressed in a well-known formal language -- linear temporal logic (LTL) -- and can specify a diversity of complex, temporally extended behaviours, including conditionals and alternative realizations. Our proposed learning approach exploits the compositional syntax and the semantics of LTL, enabling our RL agent to learn task-conditioned policies that generalize to new instructions, not observed during training. To reduce the overhead of learning LTL semantics, we introduce an environment-agnostic LTL pretraining scheme which improves sample-efficiency in downstream environments. Experiments on discrete and continuous domains target combinatorial task sets of up to $\sim10^{39}$ unique tasks and demonstrate the strength of our approach in learning to solve (unseen) tasks, given LTL instructions.