Reinforcement learning (RL) algorithms face significant challenges when dealing with long-horizon robot manipulation tasks in real-world environments due to sample inefficiency and safety issues. To overcome these challenges, we propose a novel framework, SEED, which leverages two approaches: reinforcement learning from human feedback (RLHF) and primitive skill-based reinforcement learning. Both approaches are particularly effective in addressing sparse reward issues and the complexities involved in long-horizon tasks. By combining them, SEED reduces the human effort required in RLHF and increases safety in training robot manipulation with RL in real-world settings. Additionally, parameterized skills provide a clear view of the agent's high-level intentions, allowing humans to evaluate skill choices before they are executed. This feature makes the training process even safer and more efficient. To evaluate the performance of SEED, we conducted extensive experiments on five manipulation tasks with varying levels of complexity. Our results show that \algoName significantly outperforms state-of-the-art RL algorithms in sample efficiency and safety. In addition, SEED also exhibits a substantial reduction of human effort compared to other RLHF methods. Further details and video results can be found at https://seediros23.github.io/.

翻译：强化学习（RL）算法在现实环境中处理长时域机器人操作任务时，面临样本效率低下和安全性问题的重大挑战。为克服这些挑战，我们提出了一种新型框架SEED，该框架融合了两种方法：基于人类反馈的强化学习（RLHF）和基于原始技能的强化学习。这两种方法在解决稀疏奖励问题和长时域任务的复杂性方面尤为有效。通过它们的结合，SEED减少了RLHF所需的人力投入，并提升了在现实环境中使用RL训练机器人操作的安全性。此外，参数化技能能够清晰展现智能体的高层意图，使人类能够在技能执行前对其选择进行评估。这一特性使训练过程更加安全高效。为评估SEED的性能，我们在五个复杂度各异的操作任务上进行了广泛实验。结果表明，该算法在样本效率和安全性方面显著优于最先进的RL算法。同时，与其他RLHF方法相比，SEED还大幅减少了人力投入。更多详情与视频结果请访问https://seediros23.github.io/。