DATD3: Depthwise Attention Twin Delayed Deep Deterministic Policy Gradient For Model Free Reinforcement Learning Under Output Feedback Control

원문 초록

Reinforcement learning in real-world applications often involves output-feedback settings, where the agent receives only partial state information. To address this challenge, we propose the Output-Feedback Markov Decision Process (OPMDP), which extends the standard MDP formulation to accommodate decision-making based on observation histories. Building on this framework, we introduce Depthwise Attention Twin Delayed Deep Deterministic Policy Gradient (DATD3), a novel actor-critic algorithm that employs depthwise separable convolution and multi-head attention to encode historical observations. DATD3 maintains policy expressiveness while avoiding the instability of recurrent models. Extensive experiments on continuous control tasks demonstrate that DATD3 outperforms existing memory-based and recurrent baselines under both partial and full observability.