Collaborating with language models for embodied reasoning
Reasoning in a complex and ambiguous environment is a key goal for Reinforcement Learning (RL) agents. While some sophisticated RL agents can successfully solve difficult tasks, they require a large amount of training data and often struggle to generalize to new unseen environments and new tasks. On...
Gespeichert in:
Hauptverfasser: | , , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Reasoning in a complex and ambiguous environment is a key goal for
Reinforcement Learning (RL) agents. While some sophisticated RL agents can
successfully solve difficult tasks, they require a large amount of training
data and often struggle to generalize to new unseen environments and new tasks.
On the other hand, Large Scale Language Models (LSLMs) have exhibited strong
reasoning ability and the ability to to adapt to new tasks through in-context
learning. However, LSLMs do not inherently have the ability to interrogate or
intervene on the environment. In this work, we investigate how to combine these
complementary abilities in a single system consisting of three parts: a
Planner, an Actor, and a Reporter. The Planner is a pre-trained language model
that can issue commands to a simple embodied agent (the Actor), while the
Reporter communicates with the Planner to inform its next command. We present a
set of tasks that require reasoning, test this system's ability to generalize
zero-shot and investigate failure cases, and demonstrate how components of this
system can be trained with reinforcement-learning to improve performance. |
---|---|
DOI: | 10.48550/arxiv.2302.00763 |