What Does a ProcGen Generalization Gap Measure? Action Rules, Convergence, and the Missing Random Floor
cs.LG, cs.AI
Submitted: 2026-09-26
Updated: 2026-09-26
Terminology
Sources
- Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments
- Reliability of CKA as a Similarity Measure in Deep Learning
- Improving Generalization on the ProcGen Benchmark with Simple Architectural Changes and Scale
- Proximal Policy Optimization with Adaptive Exploration
- Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark
- Analyzing Reinforcement Learning Benchmarks with Random Weight Guessing
- PPO-BR: Dual-Signal Entropy-Reward Adaptation for Trust Region Policy Optimization
- Robust Policy Optimization in Deep Reinforcement Learning
- Impoola: The Power of Average Pooling for Image-Based Deep Reinforcement Learning
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks