Modular and Lifelong Learning for Developing General Purpose Robotic Agents

强化学习或从交互中学习是一种很有前途的通才机器人，可以通过额外的训练来学习和提高性能。该研究计划的长期目标（10-15年）是通过以下方式解决将交互方法学习应用于真实的机器人代理的两个限制：（1）学习算法，以实现真实的世界中的有效训练;（2）开发原则性通用奖励功能，以鼓励机器人学习与人类相似的各种行为。这项研究是由解决方案，不过分受模拟的影响，旨在针对方法，在真实的世界中的真实的机器人，以避免潜在的偏见。这些真实世界的假设对学习算法引入了额外的约束。然而，这些限制导致了一个更独立的学习系统，具有更像人类的学习能力。该研究计划有三个关键的短期（5年）目标，这些目标是限制（RL）范式生产具有人类水平技能的代理人的障碍。 目标1通过学习模块化和可重用的决策过程，构建能够跨MDP和形态学进行泛化的算法。目标2：开发持续学习系统，使智能体能够在现实世界中进行功能和独立的训练。目标3：创建通用和有原则的奖励函数，使智能体能够学习对未来任务有用的各种技能。

Reinforcement learning or learning from interaction is a promising route to generalists robots that can learn and improve their performance with additional training. The long-term objective (10-15 years) of this research program is to address two limitations in applying learning from interaction methods on real robotic agents via (1) learning algorithms to enable efficient training in the real world and (2) develop principled general purpose reward functions to encourage robots to learn diverse behaviours similar to humans. This research is directed by solutions that are not overly influenced by simulation and aims to target methods that work on real robots in the real world to avoid potential bias. These real-world assumptions introduce additional constraints on the learning algorithms. However, these constraints induce a more independent learning system with more human-like learning capabilities. This research program has three key short-term (5 year) objectives that are hurdles limiting the (RL) paradigm from producing agents with human-level skill. Aim 1 Build algorithms that enable generalization across MDPs and morphologies by learning modular and reusable decision making processes. Aim 2: Develop continual learning systems to enable agents that can functionally and independently train in the real-world. Aim 3: Create general and principled reward functions that enable agents to learn diverse skills that are useful for future tasks.