mlsanityData to 7 Oct 2026

Stein Variational Policy Gradient

arXiv 1704.02399 ↗First posted 7 Apr 2017cs.LGcited by 42

Not on the map. Why?

Abstract (arXiv)

Policy gradient methods have been successfully applied to many complex reinforcement learning problems. However, policy gradient methods suffer from high variance, slow convergence, and inefficient exploration. In this work, we introduce a maximum entropy policy optimization framework which explicitly encourages parameter exploration, and show that this framework can be reduced to a Bayesian inference problem. We then propose a novel Stein variational policy gradient method (SVPG) which combines existing policy gradient methods and a repulsive functional to generate a set of diverse but well-behaved policies. SVPG is robust to initialization and can easily be implemented in a parallel manner. On continuous control problems, we find that implementing SVPG on top of REINFORCE and advantage actor-critic algorithms improves both average return and data efficiency.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 12; 2023: 5; 2024: 6; 2025: 5; 2026: 3.

42 papers.

Sort:

By area:

  1. 2023Recent Advances in Optimal Transport for Machine Learningcited by 66
  2. 2021Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domaincited by 57
  3. 2021Robot Learning from Randomized Simulations: A Reviewcited by 56
  4. 2022Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimalitycited by 35
  5. 2021Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimizationcited by 22
  6. 2021Bayesian Sequential Optimal Experimental Design for Nonlinear Models Using Policy Gradient Reinforcement Learningcited by 22
  7. 2022A Finite-Particle Convergence Rate for Stein Variational Gradient Descentcited by 22
  8. 2021A Convergence Theory for SVGD in the Population Limit under Talagrand's Inequality T1cited by 21
  9. 2022Combining Evolution and Deep Reinforcement Learning for Policy Search: a Surveycited by 20
  10. 2022Regularized Stein Variational Gradient Flowcited by 18
  11. 2024S2AC: Energy-Based Reinforcement Learning with Stein Soft Actor Criticcited by 18
  12. 2022Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Conditioncited by 16
30 more
  1. 2022Amortized Variational Inference: A Systematic Reviewcited by 16
  2. 2023Diversifying AI: Towards Creative Chess with AlphaZerocited by 15
  3. 2024CaDRE: Controllable and Diverse Generation of Safety-Critical Driving Scenarios using Real-World Trajectoriescited by 11
  4. 2021DR2L: Surfacing Corner Cases to Robustify Autonomous Driving via Domain Randomization Reinforcement Learningcited by 10
  5. 2022Reinforcement Learning Algorithms: An Overview and Classificationcited by 10
  6. 2023GAD-PVI: A General Accelerated Dynamic-Weight Particle-Based Variational Inference Frameworkcited by 9
  7. 2022ASPiRe:Adaptive Skill Priors for Reinforcement Learningcited by 7
  8. 2022Autonomous Unmanned Aerial Vehicle Navigation using Reinforcement Learning: A Systematic Reviewcited by 6
  9. 2023Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximationcited by 6
  10. 2022Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learningcited by 5
  11. 2021Online reinforcement learning with sparse rewards through an active inference capsulecited by 3
  12. 2021Loss function based second-order Jensen inequality and its application to particle variational inferencecited by 3
  13. 2021DROMO: Distributionally Robust Offline Model-based Policy Optimizationcited by 3
  14. 2023Learning Rate Free Sampling in Constrained Domainscited by 3
  15. 2024How to Choose a Reinforcement-Learning Algorithmcited by 3
  16. 2022Improved Stein Variational Gradient Descent with Importance Weightscited by 2
  17. 2024Long-time asymptotics of noisy SVGD outside the population limitcited by 2
  18. 2024Stein Variational Evolution Strategiescited by 2
  19. 2021Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptationcited by 1
  20. 2021Automated and Autonomous Experiment in Electron and Scanning Probe Microscopycited by 1
  21. 2024Bayesian Deep Learning for Remaining Useful Life Estimation via Stein Variational Gradient Descentcited by 1
  22. 2025Soft Quality-Diversity Optimizationcited by 1
  23. 2022Quantification before Selection: Active Dynamics Preference for Robust Reinforcement Learningcited by 0
  24. 2025Trajectory First: A Curriculum for Discovering Diverse Policiescited by 0
  25. 2025Branching Stein Variational Gradient Descent for sampling multimodal distributionscited by 0
  26. 2025Frictional Q-Learningcited by 0
  27. 2025Adaptive Kernel Selection for Stein Variational Gradient Descentcited by 0
  28. 2026Optimize Wider, Not Deeper: Consensus Aggregation for Policy Optimizationcited by 0
  29. 2026POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensemblescited by 0
  30. 2026Variational Proximal Policy Optimizationcited by 0