Reward Inflation: A Healthy Stimulus for Reinforcement Learning
cs.LG
Submitted: 2026-10-01
Updated: 2026-10-01
Terminology
Sources
- Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle
- Return-based Scaling: Yet Another Normalisation Trick for Deep RL
- Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning
- A survey on intrinsic motivation in reinforcement learning
- Reward Shaping via Meta-Learning
- From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learning
- Curriculum Reinforcement Learning for Complex Reward Functions
- Proximal Policy Optimization Algorithms
- Adapting to Reward Progressivity via Spectral Reinforcement Learning
- Prioritized Experience Replay
- Experience Replay Optimization
- Boosting Soft Actor-Critic: Emphasizing Recent Experience without Forgetting the Past
- Reward Prediction Error Prioritisation in Experience Replay: The RPE-PER Method
- Demystifying the Recency Heuristic in Temporal-Difference Learning
- Disentangling the Causes of Plasticity Loss in Neural Networks
- The effect of Target Normalization and Momentum on Dying ReLU
- The Resurrection of the ReLU
- Soft Actor-Critic Algorithms and Applications
- A survey on recently proposed activation functions for Deep Learning
- Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks