Recent works successfully leveraged Large Language Models' (LLM) abilities to capture abstract knowledge about world's physics to solve decision-making problems. Yet, the alignment between LLMs' knowledge and the environment can be wrong and limit functional competence due to lack of grounding. In this paper, we study an approach to achieve this alignment through functional grounding: we consider an agent using an LLM as a policy that is progressively updated as the agent interacts with the environment, leveraging online Reinforcement Learning to improve its performance to solve goals. Using an interactive textual environment designed to study higher-level forms of functional grounding, and a set of spatial and navigation tasks, we study several scientific questions: 1) Can LLMs boost sample efficiency for online learning of various RL tasks? 2) How can it boost different forms of generalization? 3) What is the impact of online learning? We study these questions by functionally grounding several variants (size, architecture) of FLAN-T5.
Reinforcement learning (RL) in long horizon and sparse reward tasks is notoriously difficult and requires a lot of training steps. A standard solution to speed up the process is to leverage additional reward signals, shaping it to better guide the learning process. In the context of language-conditioned RL, the abstraction and generalisation properties of the language input provide opportunities for more efficient ways of shaping the reward. In this paper, we leverage this idea and propose an automated reward shaping method where the agent extracts auxiliary objectives from the general language goal. These auxiliary objectives use a question generation (QG) and question answering (QA) system: they consist of questions leading the agent to try to reconstruct partial information about the global goal using its own trajectory. When it succeeds, it receives an intrinsic reward proportional to its confidence in its answer. This incentivizes the agent to generate trajectories which unambiguously explain various aspects of the general language goal. Our experimental study shows that this approach, which does not require engineer intervention to design the auxiliary objectives, improves sample efficiency by effectively directing exploration.
We present VisualHints, a novel environment for multimodal reinforcement learning (RL) involving text-based interactions along with visual hints (obtained from the environment). Real-life problems often demand that agents interact with the environment using both natural language information and visual perception towards solving a goal. However, most traditional RL environments either solve pure vision-based tasks like Atari games or video-based robotic manipulation; or entirely use natural language as a mode of interaction, like Text-based games and dialog systems. In this work, we aim to bridge this gap and unify these two approaches in a single environment for multimodal RL. We introduce an extension of the TextWorld cooking environment with the addition of visual clues interspersed throughout the environment. The goal is to force an RL agent to use both text and visual features to predict natural language action commands for solving the final task of cooking a meal. We enable variations and difficulties in our environment to emulate various interactive real-world scenarios. We present a baseline multimodal agent for solving such problems using CNN-based feature extraction from visual hints and LSTMs for textual feature extraction. We believe that our proposed visual-lingual environment will facilitate novel problem settings for the RL community.