The paper investigates whether enhancing goal representations improves goal-conditioned reinforcement learning (GCRL) performance. By creating an exact temporal-distance goal representation in deterministic mazes and systematically degrading its geometric quality, the authors find that changes in goal representation have little effect on performance. In contrast, degrading the agent’s current state representation more than doubles failure rates, indicating that state representation is the critical bottleneck. The study further demonstrates that simple random Fourier positional encodings can significantly boost performance on challenging navigation tasks without additional map or objective modifications.
By Syed Nazmus Sakib, Abdul Monaf Chowdhury, Nafiul Haque, Shifat E Arman, Md Mehedi Hasan
arXiv:2607. 23854v1 Announce Type: new Abstract: Humans often find good solutions to combinatorial optimization problems that are computationally hard even for advanced computer algorithms.
By Haijiang Yan, Jian-Qiao Zhu, Liqiang Huang, Ming Meng
arXiv:2609.36238v1 Announce Type: new
Abstract: A goal that is close in space can be far away in time. Obstacles, terrain, and the agent's own capabilities determine how long it takes to get there. Y...
By Nico Bohlinger, Jan Peters
arXiv:2608. 00270v2 Announce Type: replace Abstract: Neural Combinatorial Optimization (NCO) techniques have emerged as a highly efficient alternative to traditional exact algorithms for solving routing problems such as the Traveling Salesman Problem (TSP).
By David Aguado, Daniel Fuertes, Carlos R. del-Blanco, Fernando Jaureguizar
arXiv:2610.20409v1 Announce Type: new
Abstract: We develop a self-supervised reinforcement learning algorithm that learns to build towers of up to eight cubes from scratch, without prior data, reward...
By Jonghae Park, Sungil Son, Jonghun Shin, Junseo Lee, H. Jin Kim, Benjamin Eysenbach
The paper introduces Survival Reinforcement Learning (SRL), an online classification-based method that extends the survival value learning framework to maximize an agent’s dwell time at target goals. SRL addresses limitations of contrastive reinforcement learning (CRL) in long-horizon, goal-conditioned tasks by avoiding the uniformity-tolerance dilemma and reducing undesirable bang-bang control behaviors. Across robotic benchmarks, SRL matches CRL on manipulation tasks and outperforms it by 2x to 8x on stable, long-horizon locomotion tasks, suggesting classification-based approaches are a promising direction for scaling reinforcement learning.
By Franki Nguimatsia-Tiofack, Fabian Schramm, Th\'eotime Le Hellard, Justin Carpentier
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:2608. 07870v1 Announce Type: new Abstract: Improving sample efficiency remains a core challenge in reinforcement learning (RL), especially in real-world settings like robotics, where data collection is costly.
By Donghu Kim, Youngdo Lee, Hojoon Lee, Johan Obando-Ceron, Byungkun Lee, Aaron Courville, Pablo Samuel Castro, Jaegul Choo, Clare Lyle
arXiv:2609.38598v1 Announce Type: new
Abstract: Partially observable environments pose a fundamental challenge in deep reinforcement learning, requiring agents to compress temporal information from o...
By Sathya Kamesh Bhethanabhotla, Efstratios Gavves, Andr\'e Biedenkapp
arXiv:2606. 01868v1 Announce Type: new Abstract: Reinforcement Learning (RL) has long served as a model for goal-directed animal behavior in neuroscience.
By Manu Srinath Halvagal, Sebastian Lee, SueYeon Chung
arXiv:2605. 08732v2 Announce Type: replace-cross Abstract: Modern vision-based world models can represent observations as compact yet expressive latent manifolds, but fast goal-oriented planning in these spaces remains challenging.
By Hoang Nguyen, Xiaohao Xu, Xiaonan Huang
arXiv:2602. 05999v3 Announce Type: replace Abstract: How does the amount of compute available to a reinforcement learning (RL) policy affect its learning?
By Raj Ghugare, Micha{\l} Bortkiewicz, Alicja Ziarko, Benjamin Eysenbach