paper-with-me

홈 › Papers

Self-supervised Reinforcement Learning with Independently Controllable Subgoals

2021-09-09 · Andrii Zadaianchuk, Georg Martius, Fanny Yang

To successfully tackle challenging manipulation tasks, autonomous agents must learn a diverse set of skills and how to combine them. Recently, self-supervised agents that set their own abstract goals by exploiting the discovered structure in the environment were shown to perform well on many different tasks. In particular, some of them were applied to learn basic manipulation skills in compositional multi-object environments. However, these methods learn skills without taking the dependencies between objects into account. Thus, the learned skills are difficult to combine in realistic environments. We propose a novel self-supervised agent that estimates relations between environment components and uses them to independently control different parts of the environment state. In addition, the estimated relations between objects can be used to decompose a complex goal into a compatible sequence of subgoals. We show that, by using this framework, an agent can efficiently and automatically learn manipulation tasks in multi-object environments with different relations between objects.

📄 PDF Abstract BibTeX arXiv:2109.04150

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Goal-Conditioned Reinforcement Learning with Disentanglement-based Reachability Planning

2023-07-20 · Zhifeng Qian, Mingyu You, Hongjun Zhou, Xuanhui Xu 외

Goal-Conditioned Reinforcement Learning (GCRL) can enable agents to spontaneously set diverse goals to learn a set of skills. Despite the excellent works proposed in various fields, reaching distant goals in temporally e…

Disentanglementreinforcement-learningReinforcement Learning

Subgoal Discovery for Hierarchical Dialogue Policy Learning

2018-04-20 · EMNLP 2018 10 · Da Tang, Xiujun Li, Jianfeng Gao, Chong Wang 외

Developing agents to engage in complex goal-oriented dialogues is challenging partly because the main learning signals are very sparse in long conversations. In this paper, we propose a divide-and-conquer approach that d…

Hierarchical Reinforcement LearningReinforcement Learning

Subgoal Graph-Augmented Planning for LLM-Guided Open-World Reinforcement Learning

2025-11-26 · Shanwei Fan, Bin Zhang, Zhiwei Xu, Yingxuan Teng 외 arxiv

Large language models (LLMs) offer strong high-level planning capabilities for reinforcement learning (RL) by decomposing tasks into subgoals. However, their practical utility is limited by poor planning-execution alignm…

Reinforcement Learning

Learning Representations in Model-Free Hierarchical Reinforcement Learning

2018-10-23 · Jacob Rafati, David C. Noelle

Common approaches to Reinforcement Learning (RL) are seriously challenged by large-scale applications involving huge state spaces and sparse delayed reward feedback. Hierarchical Reinforcement Learning (HRL) methods atte…

Hierarchical Reinforcement LearningmodelMontezuma's Revengereinforcement-learning+2

From Pixels to Factors: Learning Independently Controllable State Variables for Reinforcement Learning

2025-10-02 · Rafael Rodriguez-Sanchez, Cameron Allen, George Konidaris arxiv

Algorithms that exploit factored Markov decision processes are far more sample-efficient than factor-agnostic methods, yet they assume a factored representation is known a priori -- a requirement that breaks down when th…

Reinforcement LearningContrastive Learning