In this paper, we propose a divide-and-conquer approach that discovers and exploits the hidden structure of the task to enable efficient policy learning.
Apr 20, 2018 · In this paper, we propose a divide-and-conquer approach that discovers and exploits the hidden structure of the task to enable efficient policy learning.
Oct 31, 2018 · We then use these subgoals to learn a hierarchical policy which consists of 1) a top-level policy that selects among subgoals, and 2) a low- ...
Abstract. Reinforcement learning addresses the problem of learning to select actions in order to maximize an agent's performance in unknown environments.
Missing: Dialogue | Show results with:Dialogue
Oct 31, 2018 · Developing conversational agents to engage in complex dialogues is challenging partly because the dialogue policy needs to explore a large ...
Jan 15, 2024 · Connected Papers is a visual tool to help researchers and applied scientists find academic papers relevant to their field of work.
Sep 22, 2018 · Developing agents to engage in complex goal- oriented dialogues is challenging partly be- cause the main learning signals are very sparse.
Hierarchical Dialogue Policy Learning using Flexible State Transitions and ... Subgoal Discovery for Hierarchical Dialogue Policy Learning. January 2018.
Subgoal discovery. Identifying useful subgoals to guide training (low-level) policy has long been recognized as an effective way to solve complex RL problems [ ...
Jun 30, 2023 · This paper presents a method by which a reinforcement learning agent can discover subgoals with certain structural properties. By discovering ...
Missing: Dialogue | Show results with:Dialogue