决策模型引导训练：用 DM 初始化 RL 策略提升稀疏奖励任务表现
The Blindfolded Controller: Decision Model-Guided Training for Reinforcement Learning
把决策模型当 RL 的起跑器：智能体第一局就拿到奖励，7 个任务全赢纯 RL，还附了怎么写任务描述的指南。
arXiv 论文提出 Decision Model-Guided Training（DMGT），利用决策模型（DM）根据环境和任务描述直接生成初始策略，再由强化学习从奖励信号继续优化。该方法让智能体从首个 episode 起就能到达目标并获得奖励，避免从零探索。在 7 个稀疏奖励任务实验中，DMGT 在全部 7 个任务上超过 RL，在其中 5 个上超过 DM。论文还基于消融实验给出了向 DM 描述环境和任务的完整指南。
The Blindfolded Controller: Decision Model-Guided Training for Reinforcement Learning
Reinforcement learning (RL) provides a framework for continuous improvement through interaction with an environment. However, RL agents struggle against tasks that offer exploration challenges and sparse rewards, because learning efficient policies from scratch is slow and sample-inefficient. In contrast, decision models (DMs), given a description of the environment and task, can perform well in sparse-reward tasks, but, as they do not learn from reward, they are not able to improve towards the optimal solution. In this paper, we present Decision Model-Guided Training (DMGT), a technique that uses a DM with a description of the environment and task to initialise an RL policy, combining the DM's ability to act without training with RL's ability to improve from reward. Instead of exploring from scratch, the agent reaches the goal and receives reward from its first episodes, and RL then improves its policy beyond what the DM achieves. We demonstrate through experiments on seven tasks that our approach outperforms RL in all seven and DM in five. In addition, we provide comprehensive guidelines, derived from ablation studies, for describing an environment and task to a DM.