Compositional Instruction Following with Language Models and Reinforcement Learning
This addresses the problem of sample efficiency in language-conditioned reinforcement learning for AI agents, representing an incremental improvement with strong specific gains.
The paper tackles the challenge of combining reinforcement learning with language grounding for compositional instruction following by introducing CERLLA, a method that reduces sample complexity and achieves a 92% success rate, outperforming a non-compositional baseline at 80%.
Combining reinforcement learning with language grounding is challenging as the agent needs to explore the environment while simultaneously learning multiple language-conditioned tasks. To address this, we introduce a novel method: the compositionally-enabled reinforcement learning language agent (CERLLA). Our method reduces the sample complexity of tasks specified with language by leveraging compositional policy representations and a semantic parser trained using reinforcement learning and in-context learning. We evaluate our approach in an environment requiring function approximation and demonstrate compositional generalization to novel tasks. Our method significantly outperforms the previous best non-compositional baseline in terms of sample complexity on 162 tasks designed to test compositional generalization. Our model attains a higher success rate and learns in fewer steps than the non-compositional baseline. It reaches a success rate equal to an oracle policy's upper-bound performance of 92%. With the same number of environment steps, the baseline only reaches a success rate of 80%.