홈 › Papers

Compositional Transfer in Hierarchical Reinforcement Learning

2019-06-26 · Markus Wulfmeier, Abbas Abdolmaleki, Roland Hafner, Jost Tobias Springenberg, Michael Neunert, Tim Hertweck, Thomas Lampe, Noah Siegel, Nicolas Heess, Martin Riedmiller

The successful application of general reinforcement learning algorithms to real-world robotics applications is often limited by their high data requirements. We introduce Regularized Hierarchical Policy Optimization (RHPO) to improve data-efficiency for domains with multiple dominant tasks and ultimately reduce required platform time. To this end, we employ compositional inductive biases on multiple levels and corresponding mechanisms for sharing off-policy transition data across low-level controllers and tasks as well as scheduling of tasks. The presented algorithm enables stable and fast learning for complex, real-world domains in the parallel multitask and sequential transfer case. We show that the investigated types of hierarchy enable positive transfer while partially mitigating negative interference and evaluate the benefits of additional incentives for efficient, compositional task solutions in single task domains. Finally, we demonstrate substantial data-efficiency and final performance gains over competitive baselines in a week-long, physical robot stacking experiment.

📄 PDF Abstract BibTeX arXiv:1906.11228

Code (0)

등록된 구현이 없습니다.

Tasks

General Reinforcement Learning Hierarchical Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)SchedulingTransfer Learning

Learning Functionally Decomposed Hierarchies for Continuous Navigation Tasks

2019-09-25 · Lukas Jendele, Sammy Christen, Emre Aksan, Otmar Hilliges

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-control Continuous Control Decision Making Hierarchical Reinforcement Learning+4

Multi-task Hierarchical Adversarial Inverse Reinforcement Learning

2023-05-22 · Jiayu Chen, Dipesh Tamboli, Tian Lan, Vaneet Aggarwal

Multi-task Imitation Learning (MIL) aims to train a policy capable of performing a distribution of tasks based on multi-task expert demonstrations, which is essential for general-purpose robots. Existing MIL algorithms s…

Imitation Learning Multi-Task Learning reinforcement-learning Reinforcement Learning

Efficient Multi-Task and Transfer Reinforcement Learning with Parameter-Compositional Framework

2023-06-02 · Lingfeng Sun, Haichao Zhang, Wei Xu, Masayoshi Tomizuka

In this work, we investigate the potential of improving multi-task training and also leveraging it for transferring in the reinforcement learning setting. We identify several challenges towards this goal and propose a tr…

reinforcement-learning Reinforcement Learning Transfer Reinforcement Learning

Language as an Abstraction for Hierarchical Deep Reinforcement Learning

2019-06-18 · NeurIPS 2019 12 · Yiding Jiang, Shixiang Gu, Kevin Murphy, Chelsea Finn

Solving complex, temporally-extended tasks is a long-standing problem in reinforcement learning (RL). We hypothesize that one critical element of solving such problems is the notion of compositionality. With the ability …

Deep Reinforcement Learning Instruction Following MuJoCo Object+4

HiCoGen: Hierarchical Compositional Text-to-Image Generation in Diffusion Models via Reinforcement Learning

2025-11-25 · Hongji Yang, Yucheng Zhou, Wencheng Han, Runzhou Tao 외 arxiv

Recent advances in diffusion models have demonstrated impressive capability in generating high-quality images for simple prompts. However, when confronted with complex prompts involving multiple objects and hierarchical …

Text-to-Image Generation Reinforcement Learning