← Back to all news
arXiv AI By Junhyeon Bae, Jaebak Hwang, Gwanwoo Choi, Minung Kim, Seungyul Han

Escaping Path Mirages in Offline Goal-Conditioned Reinforcement Learning

Read the original on arXiv AI →

The paper introduces Branch-aware Graph Planning (BGP), a method for offline goal-conditioned reinforcement learning that tackles the problem of path mirages in stochastic, long-horizon environments. BGP models stochastic branching by treating high-variability points as graph nodes and learns goal-conditioned edges with segmented learning to avoid unreliable branches and reduce unnecessary stochasticity. Experiments on diverse OGBench tasks demonstrate that BGP substantially outperforms existing state-of-the-art offline goal-conditioned RL approaches.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Sep 3

Recursive Value Learning for Long-Horizon Offline Goal-Conditioned RL

The paper introduces DCRL (Divide-and-Conquer RL), a method that recursively decomposes offline goal-conditioned reinforcement learning trajectories into a balanced binary tree. By training values from the leaves up to the root, DCRL avoids noisy max-based backups and reduces bootstrap depth from linear to logarithmic, thereby limiting error accumulation. Experiments on diverse goal-reaching tasks show that DCRL outperforms prior flat offline GCRL methods, achieving a higher average score on the most challenging long-horizon OGBench tasks.

By Hyeonseong Jeon, Youngwoon Lee
reinforcement-learning
More like this →
arXiv AI
Sep 30

HorizonFlow: Variable-Length Planning for Offline Goal-Conditioned RL

HorizonFlow is a hierarchical planner for offline goal-conditioned reinforcement learning that treats the planning horizon as an output rather than a fixed input. It uses a subgoal route planner and an action-prefix controller, both employing insertion-based generation and flow matching, to jointly generate continuous plan content and its length. The method leverages the partially generated plan to guide token insertion and to steer generation toward shorter plans, achieving superior performance on Maze2D, Multi2D, and OGBench benchmarks.

By JunHyeok Oh, Zian Jang, Byung-Jun Lee
diffusionreinforcement-learningroboticsbenchmarks
More like this →
arXiv Machine Learning
Sep 11

From Connectivity to Rewards: Dense Reward Learning with Directed State Graphs

The paper introduces Graph-Guided Quasimetric Dense Reward (G2QDR), a framework that learns a state connectivity model to predict pairwise connectivity strengths in asymmetric environments. These strengths are converted into scalar auxiliary dense rewards, offering continuous guidance across hierarchical levels. G2QDR can be integrated into any existing Goal-Conditioned Hierarchical Reinforcement Learning architecture and shows empirical performance improvements in sparse reward settings with modest computational cost.

By Shuyuan Zhang, Zihan Wang, Xiao-Wen Chang, Doina Precup
reinforcement-learning
More like this →
arXiv Machine Learning
Sep 30

GTRL: Grounding Divide-and-Conquer Value Learning with Temporal Differences

Grounded Transitive RL (GTRL) is an offline goal‑conditioned reinforcement learning algorithm that improves upon divide‑and‑conquer value learning by grounding updates with a one‑step temporal‑difference (TD) target. By adding this TD target rather than replacing it, GTRL ensures every state‑goal pair receives an update and corrects bias from hindsight relabeling through reweighting based on reachability. The method was evaluated on nineteen OGBench tasks across stochastic, deterministic, and stitching environments, achieving the highest average success rate among compared approaches.

By Abdul Monaf Chowdhury, MD Sameer Iqbal Chowdhury, Shifat E Arman, Md Mehedi Hasan
reinforcement-learningsafety
More like this →