paper-with-me

홈 › Papers

Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning

2021-10-11 · Yantian Zha, Lin Guan, Subbarao Kambhampati

Our work aims at efficiently leveraging ambiguous demonstrations for the training of a reinforcement learning (RL) agent. An ambiguous demonstration can usually be interpreted in multiple ways, which severely hinders the RL-Agent from learning stably and efficiently. Since an optimal demonstration may also suffer from being ambiguous, previous works that combine RL and learning from demonstration (RLfD works) may not work well. Inspired by how humans handle such situations, we propose to use self-explanation (an agent generates explanations for itself) to recognize valuable high-level relational features as an interpretation of why a successful trajectory is successful. This way, the agent can provide some guidance for its RL learning. Our main contribution is to propose the Self-Explanation for RL from Demonstrations (SERLfD) framework, which can overcome the limitations of traditional RLfD works. Our experimental results show that an RLfD model can be improved by using our SERLfD framework in terms of training stability and performance.

📄 PDF Abstract BibTeX arXiv:2110.05286

Code (1)

yantianzha/serlfd 공식 구현 pytorch

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Masked IRL: LLM-Guided Reward Disambiguation from Demonstrations and Language

2025-11-18 · Minyoung Hwang, Alexandra Forsey-Smerek, Nathaniel Dennler, Andreea Bobu arxiv

Robots can adapt to user preferences by learning reward functions from demonstrations, but with limited data, reward models often overfit to spurious correlations and fail to generalize. This happens because demonstratio…

Reinforcement Learning

SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branch

2024-12-20 · Shengyu Feng, Yiming Yang

Mixed Integer Linear Program (MILP) solvers are mostly built upon a Branch-and-Bound (B\&B) algorithm, where the efficiency of traditional solvers heavily depends on hand-crafted heuristics for branching. The past few ye…

Imitation Learningreinforcement-learningReinforcement Learning

Demonstration Guided Multi-Objective Reinforcement Learning

2024-04-05 · Junlin Lu, Patrick Mannion, Karl Mason

Multi-objective reinforcement learning (MORL) is increasingly relevant due to its resemblance to real-world scenarios requiring trade-offs between multiple objectives. Catering to diverse user preferences, traditional re…

Multi-Objective Reinforcement Learningreinforcement-learningReinforcement Learning

ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning

2025-07-03 · Ruiyang Zhou, Shuozhe Li, Amy Zhang, Liu Leqi arxiv

Self-improvement via RL often fails on complex reasoning tasks because GRPO-style post-training methods rely on the model's initial ability to generate positive samples. Without guided exploration, these approaches merel…

Reinforcement Learning

Adaptive Language-Guided Abstraction from Contrastive Explanations

2024-09-12 · Andi Peng, Belinda Z. Li, Ilia Sucholutsky, Nishanth Kumar 외

Many approaches to robot learning begin by inferring a reward function from a set of human demonstrations. To learn a good reward, it is necessary to determine which features of the environment are relevant before determ…

Program Synthesis