Exchange Policy Optimization Algorithm for Semi-Infinite Safe Reinforcement Learning
cs.LG
Submitted: 2025-11-06
Updated: 2026-09-02
Comments: Submitted to the Journal of Machine Learning Research (JMLR), added new experiments and expanded analysis
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Exploration-Exploitation in Constrained MDPs
- Benchmarking Batch Deep Reinforcement Learning Algorithms
- Proximal Policy Optimization Algorithms
- Reward Constrained Policy Optimization
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