An Empirical Evaluation of Posterior Sampling for Constrained Reinforcement Learning
Not on the map. Why?
Abstract (arXiv)
We study a posterior sampling approach to efficient exploration in constrained reinforcement learning. Alternatively to existing algorithms, we propose two simple algorithms that are more efficient statistically, simpler to implement and computationally cheaper. The first algorithm is based on a linear formulation of CMDP, and the second algorithm leverages the saddle-point formulation of CMDP. Our empirical results demonstrate that, despite its simplicity, posterior sampling achieves state-of-the-art performance and, in some cases, significantly outperforms optimistic algorithms.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 14 of its 26 references that are in the map. First posted on arXiv 8 Sep 2022.
Builds on
14 of 26 references.
References · 14
- 2017Constrained Policy Optimizationcited by 928
- 2018Reward Constrained Policy Optimizationcited by 397
- 2015Risk-Constrained Reinforcement Learning with Percentile Risk Criteriacited by 320
- 2013(More) Efficient Reinforcement Learning via Posterior Samplingcited by 233
- 2021Reinforcement learning based recommender systems: A surveycited by 187
- 2020Exploration-Exploitation in Constrained MDPscited by 146
- 2017AI Safety Gridworldscited by 108
- 2021Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPscited by 78
- 2017Learning Unknown Markov Decision Processes: A Thompson Sampling Approachcited by 65
- 2020Constrained Upper Confidence Reinforcement Learningcited by 46
- 2020Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Losscited by 46
- 2019Value constrained model-free continuous controlcited by 34
Built on by
Citing papers per year: 2024: 1.
1 paper.