mlsanityData to 14 Oct 2026

Leveraging weights signals -- Predicting and improving generalizability in reinforcement learning

arXiv 2511.20234 ↗First posted 25 Nov 2025cs.LG cs.AIcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Generalizability of Reinforcement Learning (RL) agents (ability to perform on environments different from the ones they have been trained on) is a key problem as agents have the tendency to overfit to their training environments. In order to address this problem and offer a solution to increase the generalizability of RL agents, we introduce a new methodology to predict the generalizability score of RL agents based on the internal weights of the agent's neural networks. Using this prediction capability, we propose some changes in the Proximal Policy Optimization (PPO) loss function to boost the generalization score of the agents trained with this upgraded version. Experimental results demonstrate that our improved PPO algorithm yields agents with stronger generalizability compared to the original version.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 9 of its 18 references that are in the map. First posted on arXiv 25 Nov 2025.

Builds on

9 of 18 references.

References · 9

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2018Quantifying Generalization in Reinforcement Learningcited by 352
  4. 2018A Study on Overfitting in Deep Reinforcement Learningcited by 174
  5. 2020Predicting Neural Network Accuracy from Weightscited by 110
  6. 2019Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneckcited by 101
  7. 2020Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learningcited by 26
  8. 2022Improving Policy Optimization with Generalist-Specialist Learningcited by 20
  9. 2020Reinforcement Learning Generalization with Surprise Minimizationcited by 10

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions
  2. 2026Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents
  3. 2026Certificate-Guided Evaluation of Reinforcement Learning Generalization
  4. 2024On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning
  5. 2025Good Actions Succeed, Bad Actions Generalize: A Case Study on Why RL Generalizes Better
  6. 2026Smaller Abstract State Spaces Enable Cross-Scale Generalization in Reinforcement Learning
  7. 2025Gradient Coupling: The Hidden Barrier to Generalization in Agentic Reinforcement Learning
  8. 2025On Generalization Across Environments In Multi-Objective Reinforcement Learning