arXiv AI
Aug 11
A Unified Framework for Dynamic Reward Shaping in Reinforcement Learning
arXiv:2608. 08158v1 Announce Type: new Abstract: Sparse, delayed, and weakly informative rewards remain central obstacles to efficient reinforcement learning.
Reward Inflation: A Healthy Stimulus for Reinforcement Learning
Related stories
arXiv AI
Jul 24
Adaptive Multi-Horizon Reinforcement Learning
arXiv:2607. 20656v1 Announce Type: cross Abstract: Effective decision-making in complex and changing environments requires balancing short-term and long-term consequences.
arXiv AI
Jun 2
Decoupled Behavioral Cloning for Scalable Inductive Generalization in RL from Specifications
arXiv:2606. 00838v1 Announce Type: new Abstract: Inductive generalization is a framework for reinforcement learning (RL) generalization in which inductively related task instances admit inductively related policies.
arXiv Machine Learning
Jul 30
Meta-Learned Reward Shaping for Reinforcement Learning from Human Feedback
arXiv:2607. 26094v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is the standard approach for aligning large language models with human preferences, but its quality is limited by static, task-agnostic reward models.
arXiv AI
Jun 4
Trace-Mediated Peak Bias: Bridging Temporal Credit Assignment and Cognitive Heuristics in Deep Reinforcement Learning
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.
Hugging Face Trending Papers
Jun 3
Trace-Mediated Peak Bias: Bridging Temporal Credit Assignment and Cognitive Heuristics in Deep Reinforcement Learning
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 Machine Learning
Aug 6
Reward Structure Shapes the Interaction Between Episodic Exploration and Neural Memory in Reinforcement Learning
arXiv:2608. 05111v1 Announce Type: new Abstract: In partially observable reinforcement learning, agents face a dual bottleneck: they must explore to encounter rewarding states and retain that experience in memory to optimize their policies.
arXiv Machine Learning
Oct 3
Make Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL
The paper introduces Density-Aware Reward Aggregation (DARA), a method that adjusts reward weighting in multi-reward reinforcement learning based on the density of active rewards within rollout batches. By applying an inverse-square-root density correction, DARA gives more weight to less frequently active rewards, enabling faster learning of targeted behaviors. Experiments on tool calling and mathematical reasoning demonstrate that DARA achieves comparable final performance while reducing training steps by up to 26% and 65% respectively.
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
Jun 25
Stagnant Neuron: Towards Understanding the Plasticity Loss in Multi-Agent Reinforcement Learning Value Factorization Methods
arXiv:2606. 25335v1 Announce Type: new Abstract: Multi-Agent Reinforcement Learning (MARL) value factorization methods can suffer from a loss of plasticity, gradually failing to adapt when transferring to new task instances.
arXiv Machine Learning
Oct 7
Revisiting Temporal Regularization for Smooth Control in Deep Reinforcement Learning
arXiv:2610.07910v1 Announce Type: new Abstract: Deep Reinforcement Learning policies can produce nonsmooth action oscillations that hinder deployment on physical robots. Existing architectural and pe...
arXiv AI
Jul 3
Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates
arXiv:2605. 11020v2 Announce Type: replace-cross Abstract: Inverse reinforcement learning (IRL) is typically formulated as maximizing entropy subject to matching the distribution of expert trajectories.