mlsanityData to 14 Oct 2026

ATLAS: Adaptive Topological Learning with Abstract Successors for Continual Learning

arXiv 2608.04334 ↗First posted 5 Aug 2026cs.LG cs.AIcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Contemporary model-free reinforcement learning algorithms can achieve very high performance, but have low sample efficiency and are not robust to changes in the environment. Model-based algorithms have much higher sample efficiency, but still fail when the environment shifts. This paper introduces Adaptive Topological Learning with Abstract Successors (ATLAS) to combat these challenges. ATLAS uses a Grow When Required network with Successor Features in order to achieve high sample efficiency while also robustly tackling catastrophic forgetting. We evaluate ATLAS in spatial navigation tasks, benchmarking its performance against common on-policy and off-policy algorithms. Our empirical results demonstrate that by structurally decoupling transition dynamics from the reward signal, ATLAS achieves near-instantaneous adaptation to new goals and can exhibit positive backward transfer, significantly outperforming baseline methods in non-stationary environments.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 11 of its 17 references that are in the map. First posted on arXiv 5 Aug 2026.

Builds on

11 of 17 references.

References · 11

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  3. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  4. 2018World Modelscited by 1,513
  5. 2016Progressive Neural Networkscited by 1,361
  6. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 950
  7. 2016Successor Features for Transfer in Reinforcement Learningcited by 340
  8. 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 327
  9. 2018Semi-parametric Topological Memory for Navigationcited by 209
  10. 2019Search on the Replay Buffer: Bridging Planning and Reinforcement Learningcited by 194
  11. 2016Deep Reinforcement Learning with Successor Features for Navigation across Similar Environmentscited by 50

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Hierarchical Subspaces of Policies for Continual Offline Reinforcement Learning
  2. 2025Continual Learning, Not Training: Online Adaptation For Agents
  3. 2026Stochastic Dynamics on Persistence Diagram Space via Reinforcement Learning
  4. 2026Topology-Aware State Abstraction with Tangle Cores for Markov Decision Processes
  5. 2026The Global Neural World Model: Spatially Grounded Discrete Topologies for Action-Conditioned Planning
  6. 2025A Continual Offline Reinforcement Learning Benchmark for Navigation Tasks
  7. 2025ETP-R1: Evolving Topological Planning with Reinforcement Fine-tuning for Vision-Language Navigation in Continuous Environments
  8. 2024Hierarchical Orchestra of Policies