paper-with-me

Papers

Learning Goal-Conditioned Policies from Sub-Optimal Offline Data via Metric Learning

2024-02-16 · Alfredo Reichlin, Miguel Vasco, Hang Yin, Danica Kragic

We address the problem of learning optimal behavior from sub-optimal datasets for goal-conditioned offline reinforcement learning. To do so, we propose the use of metric learning to approximate the optimal value function for goal-conditioned offline RL problems under sparse rewards, invertible actions and deterministic transitions. We introduce distance monotonicity, a property for representations to recover optimality and propose an optimization objective that leads to such property. We use the proposed value function to guide the learning of a policy in an actor-critic fashion, a method we name MetricRL. Experimentally, we show that our method estimates optimal behaviors from severely sub-optimal offline datasets without suffering from out-of-distribution estimation errors. We demonstrate that MetricRL consistently outperforms prior state-of-the-art goal-conditioned RL methods in learning optimal policies from sub-optimal offline datasets.

📄 PDF Abstract BibTeX arXiv:2402.10820

Code (0)

등록된 구현이 없습니다.

Tasks

Metric LearningOffline RLreinforcement-learning

Similar Papers 제목 키워드 기반

Stitching Sub-Trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL

2024-02-11 · Sungyoon Kim, Yunseon Choi, Daiki E. Matsunaga, Kee-Eung Kim

Offline Goal-Conditioned Reinforcement Learning (Offline GCRL) is an important problem in RL that focuses on acquiring diverse goal-oriented skills solely from pre-collected behavior datasets. In this setting, the reward…

Offline RL

STO-RL: Offline RL under Sparse Rewards via LLM-Guided Subgoal Temporal Order

2026-01-13 · Chengyang Gu, Yuxin Pan, Hui Xiong, Yize Chen arxiv

Offline reinforcement learning (RL) enables policy learning from pre-collected datasets, avoiding costly and risky online interactions, but it often struggles with long-horizon tasks involving sparse rewards. Existing go…

Reinforcement LearningOffline RL

Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning

2026-04-10 · Zhiqiang Dong, Teng Pang, Rongjian Xu, Guoqiang Wu arxiv

Offline goal-conditioned reinforcement learning (GCRL) is a practical reinforcement learning paradigm that aims to learn goal-conditioned policies from reward-free offline data. Despite recent advances in hierarchical ar…

Reinforcement Learning

Goal-Conditioned Data Augmentation for Offline Reinforcement Learning

2024-12-29 · Xingshuai Huang, Di Wu Member, Benoit Boulet

Offline reinforcement learning (RL) enables policy learning from pre-collected offline datasets, relaxing the need to interact directly with the environment. However, limited by the quality of offline datasets, it genera…

D4RLData AugmentationOffline RLreinforcement-learning+3

Goal-conditioned Offline Reinforcement Learning through State Space Partitioning

2023-03-16 · Mianchu Wang, Yue Jin, Giovanni Montana

Offline reinforcement learning (RL) aims to infer sequential decision policies using only offline datasets. This is a particularly difficult setup, especially when learning to achieve multiple different goals or outcomes…

Inductive Biasreinforcement-learningReinforcement LearningReinforcement Learning (RL)