Learning Functionally Decomposed Hierarchies for Continuous Control Tasks with Path Planning
We present HiDe, a novel hierarchical reinforcement learning architecture that successfully solves long horizon control tasks and generalizes to unseen test scenarios. Functional decomposition between planning and low-level control is achieved by explicitly separating the state-action spaces across the hierarchy, which allows the integration of task-relevant knowledge per layer. We propose an RL-based planner to efficiently leverage the information in the planning layer of the hierarchy, while the control layer learns a goal-conditioned control policy. The hierarchy is trained jointly but allows for the modular transfer of policy layers across hierarchies of different agents. We experimentally show that our method generalizes across unseen test environments and can scale to 3x horizon length compared to both learning and non-learning based methods. We evaluate on complex continuous control tasks with sparse rewards, including navigation and robot manipulation.
Code (0)
등록된 구현이 없습니다.
Tasks
continuous-controlContinuous ControlDecision MakingHierarchical Reinforcement LearningReinforcement LearningRobot ManipulationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Learning Functionally Decomposed Hierarchies for Continuous Navigation Tasks
Solving long-horizon sequential decision making tasks in environments with sparse rewards is a longstanding problem in reinforcement learning (RL) research. Hierarchical Reinforcement Learning (HRL) has held the promise …
continuous-controlContinuous ControlDecision MakingHierarchical Reinforcement Learning+4Soft Decomposed Policy-Critic: Bridging the Gap for Effective Continuous Control with Discrete RL
Discrete reinforcement learning (RL) algorithms have demonstrated exceptional performance in solving sequential decision tasks with discrete action spaces, such as Atari games. However, their effectiveness is hindered wh…
Atari Gamescontinuous-controlContinuous ControlReinforcement Learning (RL)Behavior Trees in Robot Control Systems
In this paper we will give a control theoretic perspective on the research area of behavior trees in robotics. The key idea underlying behavior trees is to make use of modularity, hierarchies and feedback, in order to ha…
Controllable Person Image Synthesis with Attribute-Decomposed GAN
This paper introduces the Attribute-Decomposed GAN, a novel generative model for controllable person image synthesis, which can produce realistic person images with desired human attributes (e.g., pose, head, upper cloth…
Attributecontinuous-controlContinuous ControlImage Generation+1Constructing Feedback Linearizable Discretizations for Continuous-Time Systems using Retraction Maps
Control laws for continuous-time dynamical systems are most often implemented via digital controllers using a sample-and-hold technique. Numerical discretization of the continuous system is an integral part of subsequent…