paper-with-me

홈 › Papers

Reinforcement Learning via Reasoning from Demonstration

2020-04-12 · Lisa Torrey

Demonstration is an appealing way for humans to provide assistance to reinforcement-learning agents. Most approaches in this area view demonstrations primarily as sources of behavioral bias. But in sparse-reward tasks, humans seem to treat demonstrations more as sources of causal knowledge. This paper proposes a framework for agents that benefit from demonstration in this human-inspired way. In this framework, agents develop causal models through observation, and reason from this knowledge to decompose tasks for effective reinforcement learning. Experimental results show that a basic implementation of Reasoning from Demonstration (RfD) is effective in a range of sparse-reward tasks.

📄 PDF Abstract BibTeX arXiv:2004.05512

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning

2026-03-10 · Tiehua Mei, Minxuan Lv, Leiyu Pan, Zhenpeng Su 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that arrive at correct answers by chance. …

Reinforcement LearningMathematical Reasoning

Escaping the Verifier: Learning to Reason via Demonstrations

2025-11-26 · Locke Cai, Max Ryabinin, Ivan Provilkov arxiv

Training Large Language Models (LLMs) to reason often relies on Reinforcement Learning (RL) with task-specific verifiers. However, many real-world reasoning-intensive tasks lack verifiers, despite offering abundant exper…

Reinforcement Learning

Demonstration Selection for In-Context Learning via Reinforcement Learning

2024-12-05 · Xubin Wang, Jianfei Wu, Yichen Yuan, Mingzhe Li 외

Diversity in demonstration selection is crucial for enhancing model generalization, as it enables a broader coverage of structures and concepts. However, constructing an appropriate set of demonstrations has remained a f…

ClassificationDiversityIn-Context LearningQ-Learning+4

Learning Reasoning Rewards from Expert Demonstrations with Inverse Reinforcement Learning

2025-10-02 · Claudio Fanconi, Nicolás Astorga, Mihaela van der Schaar arxiv

Teaching large language models (LLMs) to reason during post-training typically relies on reinforcement learning with explicit outcome- or process-based reward functions. However, in many real-world settings, obtaining or…

Reinforcement Learning

Reasoning about Counterfactuals to Improve Human Inverse Reinforcement Learning

2022-03-03 · Michael S. Lee, Henny Admoni, Reid Simmons

To collaborate well with robots, we must be able to understand their decision making. Humans naturally infer other agents' beliefs and desires by reasoning about their observable behavior in a way that resembles inverse …

counterfactualCounterfactual ReasoningDecision Makingreinforcement-learning+2