ANS: Adaptive Network Scaling For Deep Rectifier Reinforcement Learning Models

Abstract

This work provides a thorough study on how reward scaling can affect performance of deep reinforcement learning agents. In particular, we would like to answer the question that how does reward scaling affect non-saturating ReLU networks in RL? This question matters because ReLU is one of the most effective activation functions for deep learning models. We also propose an Adaptive Network Scaling framework to find a suitable scale of the rewards during learning for better performance. We conducted empirical studies to justify the solution.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywu2018ans

Related papers

• Scaling Behaviors Of LLM Reinforcement Learning Post-training: An Empirical Study In Mathematical Reasoning (2025)0.00
• Deep Q-networks For Accelerating The Training Of Deep Neural Networks (2016)0.00
• Adaptive \(q\)-network: On-the-fly Target Selection For Deep Reinforcement Learning (2024)0.00
• Scalable Reinforcement Learning For Multi-agent Networked Systems (2019)10.35
• Scalable Agent Alignment Via Reward Modeling: A Research Direction (2018)0.00
• Reward Models In Deep Reinforcement Learning: A Survey (2025)0.00
• The Art Of Scaling Reinforcement Learning Compute For Llms (2025)1.57
• Scalable Multi-agent Reinforcement Learning For Networked Systems With Average Reward (2020)0.00