Temporal credit assignment is central to both biological and artificial intelligence, yet its interaction with non-linear function approximation is poorly understood. We identify a systematic failure mode in deep reinforcement learning (RL) termed Trace-Mediated Peak Bias (TMPB).
arXiv:2606. 04735v1 Announce Type: cross Abstract: Temporal credit assignment is central to both biological and artificial intelligence, yet its interaction with non-linear function approximation is poorly understood.
arXiv:2607. 16999v1 Announce Type: cross Abstract: The Credit Assignment Problem (CAP) is fundamental to developing efficient and explainable Reinforcement Learning (RL) agents.
arXiv:2606. 04492v1 Announce Type: new Abstract: Cooperative Multi-Agent Reinforcement Learning (MARL) frequently suffers from severe reward sparsity and exploration bottlenecks.
The paper presents a framework that uses saliency maps to create hierarchical attention profiles, tracking how deep reinforcement learning agents allocate attention over time. By comparing these attention trajectories across different conditions and linking them to behavioral metrics, the study reveals algorithm‑specific biases, unintended reward‑driven strategies, and overfitting to redundant sensory inputs. Experiments on Atari 2600 games, custom Pong environments, and biomechanical visuomotor simulations demonstrate that these attention patterns correspond to measurable behavioral differences, establishing attention trajectories as a diagnostic tool beyond traditional performance metrics.
arXiv:2608. 08158v1 Announce Type: new Abstract: Sparse, delayed, and weakly informative rewards remain central obstacles to efficient reinforcement learning.
arXiv:2602. 08335v2 Announce Type: replace Abstract: Integrating Large Language Models (LLMs) with external tools via multi-agent systems offers a promising new paradigm for decomposing and solving complex problems.
arXiv:2602. 05459v2 Announce Type: replace Abstract: Offline goal-conditioned reinforcement learning (GCRL) is typically benchmarked by the best tuned success rate of each method.
arXiv:2603.02935v2 Announce Type: replace Abstract: Offline meta-reinforcement learning seeks to learn a policy that generalizes to new related tasks online. Context-based methods infer a task repres...
arXiv:2607. 19691v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards has become the predominant recipe for eliciting test-time scaling in explicit Chain-of-Thought reasoners.
arXiv:2609.17325v1 Announce Type: new Abstract: Biological cells can be viewed as individual, interacting agents whose collective dynamics give rise to adaptive behaviour at multiple levels of organi...
arXiv:2606. 20858v2 Announce Type: replace Abstract: The temporal structure of reward composition in reinforcement learning (RL) is typically hand-designed and held fixed throughout training, leaving the progression of motivational priorities largely unexplored.
Long-horizon large language model (LLM) agents are typically optimized with sparse terminal outcomes, making fine-grained credit assignment across multi-step interactions difficult. Existing approache...