# Mapping State Space using Landmarks for Universal Goal Reaching

arXiv: https://arxiv.org/abs/1908.05451 · HTML: https://mlsanity.com/paper/1908.05451/

## Key facts

- Cited by 44 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 15 Aug 2019.

## Built on by (most cited first, 30 of 44)

- [OGBench: Benchmarking Offline Goal-Conditioned RL](https://mlsanity.com/paper/2410.20092/) (2024)
- [HIQL: Offline Goal-Conditioned RL with Latent States as Actions](https://mlsanity.com/paper/2307.11949/) (2023)
- [Conservative Data Sharing for Multi-Task Offline Reinforcement Learning](https://mlsanity.com/paper/2109.08128/) (2021)
- [Horizon Reduction Makes RL Scalable](https://mlsanity.com/paper/2506.04168/) (2025)
- [Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2110.13625/) (2021)
- [MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer](https://mlsanity.com/paper/2206.10607/) (2022)
- [Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2111.09858/) (2021)
- [Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2505.12737/) (2025)
- [SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals](https://mlsanity.com/paper/2406.04784/) (2024)
- [DHRL: A Graph-Based Approach for Long-Horizon and Sparse Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2210.05150/) (2022)
- [C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks](https://mlsanity.com/paper/2110.12080/) (2021)
- [GHIL-Glue: Hierarchical Control with Filtered Subgoal Images](https://mlsanity.com/paper/2410.20018/) (2024)
- [Imitating Graph-Based Planning with Goal-Conditioned Policies](https://mlsanity.com/paper/2303.11166/) (2023)
- [Goal-Space Planning with Subgoal Models](https://mlsanity.com/paper/2206.02902/) (2022)
- [Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning](https://mlsanity.com/paper/2206.04384/) (2022)
- [CQM: Curriculum Reinforcement Learning with a Quantized World Model](https://mlsanity.com/paper/2310.17330/) (2023)
- [Adjacency constraint for efficient hierarchical reinforcement learning](https://mlsanity.com/paper/2111.00213/) (2021)
- [Guide Your Agent with Adaptive Multimodal Rewards](https://mlsanity.com/paper/2309.10790/) (2023)
- [Flattening Hierarchies with Policy Bootstrapping](https://mlsanity.com/paper/2505.14975/) (2025)
- [DisTop: Discovering a Topological representation to learn diverse and rewarding skills](https://mlsanity.com/paper/2106.03853/) (2021)
- [Offline Goal-Conditioned Reinforcement Learning with Projective Quasimetric Planning](https://mlsanity.com/paper/2506.18847/) (2025)
- [Hierarchical Robot Navigation in Novel Environments using Rough 2-D Maps](https://mlsanity.com/paper/2106.03665/) (2021)
- [Incorporating Spatial Information into Goal-Conditioned Hierarchical Reinforcement Learning via Graph Representations](https://mlsanity.com/paper/2511.10872/) (2025)
- [Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks](https://mlsanity.com/paper/2107.06405/) (2021)
- [Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout](https://mlsanity.com/paper/2309.13508/) (2023)
- [Learning to Navigate in Mazes with Novel Layouts using Abstract Top-down Maps](https://mlsanity.com/paper/2412.12024/) (2024)
- [Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning](https://mlsanity.com/paper/2604.08960/) (2026)
- [Multi-task Batch Reinforcement Learning with Metric Learning](https://mlsanity.com/paper/1909.11373/) (2019)
- [What Matters in Hierarchical Search for Combinatorial Reasoning Problems?](https://mlsanity.com/paper/2406.03361/) (2024)
- [HG2P: Hippocampus-inspired High-reward Graph and Model-Free Q-Gradient Penalty for Path Planning and Motion Control](https://mlsanity.com/paper/2410.09505/) (2024)

## Abstract (arXiv)

An agent that has well understood the environment should be able to apply its skills for any given goals, leading to the fundamental problem of learning the Universal Value Function Approximator (UVFA). A UVFA learns to predict the cumulative rewards between all state-goal pairs. However, empirically, the value function for long-range goals is always hard to estimate and may consequently result in failed policy. This has presented challenges to the learning process and the capability of neural networks. We propose a method to address this issue in large MDPs with sparse rewards, in which exploration and routing across remote states are both extremely challenging. Our method explicitly models the environment in a hierarchical manner, with a high-level dynamic landmark-based map abstracting the visited state space, and a low-level value network to derive precise local decisions. We use farthest point sampling to select landmark states from past experience, which has improved exploration compared with simple uniform sampling. Experimentally we showed that our method enables the agent to reach long-range goals at the early training stage, and achieve better performance than standard RL algorithms for a number of challenging tasks.