Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback
This work addresses the challenge of creating more natural and effective human-AI interactions in complex, embodied domains without relying on programmatic rewards, though it is incremental as it builds on existing RLHF and imitation learning methods.
The authors tackled the problem of improving multimodal interactive agents by using reinforcement learning from human feedback (RLHF) to enhance agents trained with imitation learning in a simulated 3D world, resulting in agents that improved across all metrics, including human judgment during live interactions.
An important goal in artificial intelligence is to create agents that can both interact naturally with humans and learn from their feedback. Here we demonstrate how to use reinforcement learning from human feedback (RLHF) to improve upon simulated, embodied agents trained to a base level of competency with imitation learning. First, we collected data of humans interacting with agents in a simulated 3D world. We then asked annotators to record moments where they believed that agents either progressed toward or regressed from their human-instructed goal. Using this annotation data we leveraged a novel method - which we call "Inter-temporal Bradley-Terry" (IBT) modelling - to build a reward model that captures human judgments. Agents trained to optimise rewards delivered from IBT reward models improved with respect to all of our metrics, including subsequent human judgment during live interactions with agents. Altogether our results demonstrate how one can successfully leverage human judgments to improve agent behaviour, allowing us to use reinforcement learning in complex, embodied domains without programmatic reward functions. Videos of agent behaviour may be found at https://youtu.be/v_Z9F2_eKk4.