arXiv Machine Learning
Jul 7
RL Forgets! Towards Continual Policy Optimization
arXiv:2607. 04364v1 Announce Type: new Abstract: Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks.
Continual Graph Multi-Agent Reinforcement Learning
The paper introduces Continual Graph Multi-Agent Reinforcement Learning (CGMARL), a framework that maps sequences of tasks into attributed graphs to capture task-specific structures such as network topologies or formation arrangements. It presents the Graph-based Formation (GRAFO) benchmark to illustrate forgetting in graph-based CMARL settings and proposes the Frozen Graph Encoder (FROG) to preserve past structural information using a frozen graph backbone. Experiments on GRAFO demonstrate that combining FROG with existing continual learning methods significantly improves performance across multiple CGMARL scenarios.
Related stories
arXiv AI
Aug 11
The Cell Must Go On: Agar.io for Continual Reinforcement Learning
arXiv:2505. 18347v3 Announce Type: replace-cross Abstract: Continual reinforcement learning (RL) concerns agents that are expected to learn continually, rather than converge to a policy that is then fixed for evaluation.
arXiv Machine Learning
Jun 25
Swarm-Inspired Generation of Collective Behaviors in Graph Dynamical Systems
arXiv:2606. 24958v1 Announce Type: new Abstract: Collective behavior arises when locally interacting units produce coordinated global organization, from synchronization in dynamical systems to task-relevant information flow on graphs.
arXiv AI
Jun 10
Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning
arXiv:2604. 15414v2 Announce Type: replace-cross Abstract: Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on \emph{single-model preservation}, committing to one evolving policy as the main reusable solution across tasks.
arXiv AI
Jun 19
MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning
arXiv:2506. 14990v3 Announce Type: replace Abstract: Benchmarks play a central role in reinforcement learning (RL) research, yet their computational constraints often shape what is studied.
arXiv Machine Learning
Jul 10
When Does Continual Learning Require Learning
arXiv:2607. 07847v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the next question is how can we enable models to continually learn?
arXiv Machine Learning
Oct 16
HERO: Preserving Structure and Semantics in Heterogeneous Continual Graph Learning
HERO is a heterogeneous continual graph learning framework that preserves historical knowledge at both structural and semantic levels while adapting to new tasks. It uses DiSCo to select representative target nodes and reconstruct compact heterogeneous contexts, and applies multi-level knowledge distillation to align task-conditioned predictions with semantic responses. Experiments on four datasets with three HGNN backbones show HERO achieves best or tied-best average performance while maintaining competitive forgetting.
arXiv AI
Jun 2
Task diversity produces systematic transfer but inhibits continual reinforcement learning
arXiv:2606. 00880v1 Announce Type: cross Abstract: Continual reinforcement learning aims to produce agents that learn not only to improve at their current tasks but also to adapt as task distributions change.
arXiv Machine Learning
Sep 29
HySTAR: Anchored Hypergraphs for Stable Credit Assignment in Cooperative Multi-Agent Reinforcement Learning
HySTAR is a MAPPO-based framework that addresses structural target drift in cooperative multi‑agent reinforcement learning by anchoring an overlapping sparse hypergraph as a stable high‑order value‑decomposition scaffold. It separates adaptive representation learning from a temporally consistent decomposition basis, using a spatiotemporal encoder to capture physical and task‑dependent interactions and combining temporal and structural relevance to compute agent‑specific advantages. Experiments on SMAC, GRF, Traffic Junction, and MPE show consistent improvements over MAPPO‑style, value‑factorization, and dynamic‑grouping baselines, achieving significant gains in performance and convergence speed.
arXiv AI
Jun 9
Continual Quadruped Robots Coordination via Semantic Skill Discovery
arXiv:2606. 08102v1 Announce Type: cross Abstract: Multi-quadruped coordination has attracted increasing attention due to its enhanced payload capacity, broader contact coverage, and improved adaptability to challenging tasks.
arXiv Machine Learning
Jun 25
GCT-MARL: Graph-Based Contrastive Transfer for Sample-Efficient Cooperative Multi-Agent Reinforcement Learning
arXiv:2606. 25073v1 Announce Type: new Abstract: In cooperative multi-agent reinforcement learning (MARL), from a deployment perspective, it is challenging and expensive to train agents from scratch for each new environment or task.
arXiv Machine Learning
Oct 15
MAEM: Mitigating Recency Bias via a Replay-Free, Capacity-Controlled Dynamic Mixture of Experts for Class-Incremental Graph Learning
arXiv:2610.20238v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) excel on graph-structured data but suffer catastrophic forgetting when classes arrive sequentially. In class-incremental g...