The paper introduces Generalized Implicit Temporal Abstraction (GITA), a method for goal-conditioned reinforcement learning that conditions a single value function on multiple temporal abstraction levels (k). By aggregating advantage-weighted supervision across various k values, GITA preserves both long-range signal and local resolution without committing to a single k. Experiments on OGBench show that GITA outperforms existing offline GCRL baselines, improving average success rates by 25 percentage points over HIQL and 7 percentage points over OTA.
By Pedro Robles Dutenhefner, Dikshant Shehmar, Wagner Meira Jr., Marlos C. Machado
arXiv:2608.29061v1 Announce Type: new
Abstract: Offline goal-conditioned reinforcement learning (GCRL) aims to learn policies for reaching diverse goals entirely from fixed trajectory data. Long-hori...
By Soohyun Choi, Seonvin Cho, Songnam Hong
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
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.
By Junhyeon Bae, Jaebak Hwang, Gwanwoo Choi, Minung Kim, Seungyul Han
Recent advances in generative planning have made trajectory inpainting a promising approach to offline goal-conditioned reinforcement learning. However, these methods typically specify the planning ho...
The paper introduces the World-Model Policy Arbiter (WMPA), a test‑time framework that selects among a portfolio of frozen goal‑conditioned policies by simulating each policy’s future trajectories in a learned world model and evaluating them with a shared value function. WMPA avoids frequent policy switching by committing to the chosen policy for a short interval and does not require retraining or task‑specific knowledge. On the OGBench benchmark, WMPA raises the macro‑average success rate from 44% to 58%, achieving significant improvements on 12 of 18 datasets, including large gains on cube‑double‑play and scene‑play.
By Junwei Quan, Evgenii Opryshko, Nicholas Rhinehart, Igor Gilitschenski
The paper identifies an informational curse of horizon in goal-conditioned policy learning, showing that longer goal relabeling horizons during training can hurt policy generalization and performance. Controlled experiments with oracle planners separate training horizons from test horizons, revealing that behavioral cloning policies degrade with longer horizons while reinforcement learning mitigates this effect. The authors attribute this to reduced conditional mutual information between actions and hindsight-relabeled goals, and demonstrate that distilling short-horizon policy Jacobians into long-horizon policies improves performance, especially in combinatorial manipulation tasks.
By John L. Zhou, Yuxuan Dong, Jonathan C. Kao
The paper introduces Visual Learned Distance (VLD), a framework that separates perception from policy learning for image-goal navigation. VLD trains a self-supervised distance-to-goal predictor on thousands of hours of video, then uses a reinforcement learning policy trained in simulation with a learned noise model (GeoNoise) to mimic the predictor’s errors. At deployment, the policy uses VLD predictions zero‑shot, achieving high success rates in simulated environments and on a physical robot without retraining.
By Lazar Milikic, Manthan Patel, Jonas Frey
arXiv:2608. 14332v1 Announce Type: cross Abstract: Reinforcement learning is promising for autonomous urban driving, but long-horizon goal-directed navigation asks a policy to acquire several competing behaviors at once--reaching a distant goal, tracking a route, avoiding obstacles, obeying signals--and a fixed objective gives no order in which to learn them.
By Anisa Saleem, Duksu Kim
arXiv:2609.38383v1 Announce Type: cross
Abstract: Random exploration reveals how an environment can be traversed before a goal is specified. Can this experience support long-range planning without po...
By Deqian Kong, Guangyan Sun, Sheng Cheng, Sirui Xie, Bo Pang, Jianwen Xie, Tony Geng, Caiwen Ding, Ying Nian Wu
arXiv:2610.17927v1 Announce Type: cross
Abstract: Autonomous navigation in real-world environments often requires long-horizon operation under partial observability and evolving goals. Existing maple...
By Yousef Liang, Ryan Ardalan, Yarden Goraly, Chenhao Zhu, Yue Yin, Jonas Frey, Claire Tomlin, Marco Pavone, Shankar Sastry
arXiv:2607. 13731v1 Announce Type: new Abstract: Goal-conditioned reinforcement learning hinges on how the goal is encoded.
By Xing Lei, Wenyan Yang, Xuetao Zhang, Donglin Wang