SAPIENT: Mastering Multi-turn Conversational Recommendation with Strategic Planning and Monte Carlo Tree Search
Keywords: Conversational Planning, Monte Carlo Tree Search
TL;DR: We present SAPIENT, a novel Monte Carlo Tree Search-based algorithm for conversational recommender system that is able to achieve strategic decision-making and non-myopic conversational planning and shows the state-of-the-art performance.
Abstract: Conversational Recommender Systems (CRS) proactively engage users in interactive dialogues to elicit user preferences and provide personalized recommendations. Existing methods train Reinforcement Learning (RL)-based agent with greedy action selection or sampling strategy, and may suffer from suboptimal conversational planning. To address this, we present a novel Monte Carlo Tree Search (MCTS)-based CRS framework, Strategic Action Planning with Intelligent Exploration and Non-myopic Tactics, referred to as SAPIENT. SAPIENT consists of a conversational agent (S-agent) and a conversational planner (S-planner). S-planner builds a conversational search tree with MCTS based on the initial actions proposed by S-agent to find conversation plans. The best conversation plans from S-planner are used to guide the training of S-agent, creating a self-training loop where S-agent can iteratively refine its capacity for conversational planning. Furthermore, we propose an efficient alternative SAPIENT-e for trade-off between training efficiency and performance. Extensive experiments on four benchmark datasets validate the effectiveness of our approach, showing that SAPIENT outperforms the state-of-the-art baselines. Our anonymous code and data are accessible through https://anonymous.4open.science/r/SAPIENT/.
Submission Number: 15
Loading