CORL：一个连续状态偏移动力学强化学习器
CORL: A Continuous-state Offset-dynamics Reinforcement Learner
摘要：
连续的状态空间和随机的，切换动力学表征了许多丰富的，现实世界的领域，如机器人导航在不同的地形。我们描述了一个schemcementlearning算法在这些领域的学习，并证明在某些环境下，该算法可能是近似正确的样本复杂性，规模多项式与状态空间维度。不幸的是，没有最优规划技术存在一般这样的问题，而是我们使用拟合值迭代来解决学习MDP，并包括由于近似规划在我们的范围内的错误。最后，我们报告了一个实验，使用机器人汽车驾驶在不同的地形，以证明这些动态表示充分捕捉现实世界的动态，我们的算法可以用来有效地解决这些问题。
英文摘要：
Continuous state spaces and stochastic, switching dynamics characterize a number of rich, realworld domains, such as robot navigation across varying terrain. We describe a reinforcementlearning algorithm for learning in these domains and prove for certain environments the algorithm is probably approximately correct with a sample complexity that scales polynomially with the state-space dimension. Unfortunately, no optimal planning techniques exist in general for such problems; instead we use fitted value iteration to solve the learned MDP, and include the error due to approximate planning in our bounds. Finally, we report an experiment using a robotic car driving over varying terrain to demonstrate that these dynamics representations adequately capture real-world dynamics and that our algorithm can be used to efficiently solve such problems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
