Prompt-Tuning Decision Transformer with Preference Ranking
This work addresses the problem of adapting pre-trained RL models to specific preference tasks for researchers and practitioners, representing an incremental advancement in prompt-tuning methods for RL.
The paper tackles the challenge of applying prompt-tuning to reinforcement learning by proposing Prompt-Tuning DT, which uses trajectory segments as prompts and optimizes them via black-box tuning with preference ranking, achieving comparable or better performance than full-model fine-tuning with only 0.03% of parameters learned in low-data scenarios.
Prompt-tuning has emerged as a promising method for adapting pre-trained models to downstream tasks or aligning with human preferences. Prompt learning is widely used in NLP but has limited applicability to RL due to the complex physical meaning and environment-specific information contained within RL prompts. These factors require supervised learning to imitate the demonstrations and may result in a loss of meaning after learning. Additionally, directly extending prompt-tuning approaches to RL is challenging because RL prompts guide agent behavior based on environmental modeling and analysis, rather than filling in missing information, making it unlikely that adjustments to the prompt format for downstream tasks, as in NLP, can yield significant improvements. In this work, we propose the Prompt-Tuning DT algorithm to address these challenges by using trajectory segments as prompts to guide RL agents in acquiring environmental information and optimizing prompts via black-box tuning to enhance their ability to contain more relevant information, thereby enabling agents to make better decisions. Our approach involves randomly sampling a Gaussian distribution to fine-tune the elements of the prompt trajectory and using preference ranking function to find the optimization direction, thereby providing more informative prompts and guiding the agent towards specific preferences in the target environment. Extensive experiments show that with only 0.03% of the parameters learned, Prompt-Tuning DT achieves comparable or even better performance than full-model fine-tuning in low-data scenarios. Our work contributes to the advancement of prompt-tuning approaches in RL, providing a promising direction for optimizing large RL agents for specific preference tasks.