论文标题
逆增强学习环境设计
Environment Design for Inverse Reinforcement Learning
论文作者
论文摘要
从示威活动中学习奖励功能的样本效率低。即使有大量数据，专注于从单个环境学习的当前逆增强学习方法也无法处理环境动态的轻微变化。我们通过自适应环境设计来应对这些挑战。在我们的框架中，学习者反复与专家进行互动，以前的选择环境，以尽快从该环境中的专家演示中识别奖励功能。正如我们在实验上表明的，这都可以改善样本效率和鲁棒性，以精确和近似推断。
Learning a reward function from demonstrations suffers from low sample-efficiency. Even with abundant data, current inverse reinforcement learning methods that focus on learning from a single environment can fail to handle slight changes in the environment dynamics. We tackle these challenges through adaptive environment design. In our framework, the learner repeatedly interacts with the expert, with the former selecting environments to identify the reward function as quickly as possible from the expert's demonstrations in said environments. This results in improvements in both sample-efficiency and robustness, as we show experimentally, for both exact and approximate inference.
