Conservative Optimistic Policy Optimization Via Multiple Importance Sampling

Abstract

Reinforcement Learning (RL) has been able to solve hard problems such as playing Atari games or solving the game of Go, with a unified approach. Yet modern deep RL approaches are still not widely used in real-world applications. One reason could be the lack of guarantees on the performance of the intermediate executed policies, compared to an existing (already working) baseline policy. In this paper, we propose an online model-free algorithm that solves conservative exploration in the policy optimization problem. We show that the regret of the proposed approach is bounded by \(\tilde\{\mathcal\{O\}\}(\sqrt\{T\})\) for both discrete and continuous parameter spaces.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyazize2021conservative

Related papers

• Conservative Exploration For Policy Optimization Via Off-policy Policy Evaluation (2023)0.00
• Low-switching Policy Gradient With Exploration Via Online Sensitivity Sampling (2023)0.00
• Optimistic Natural Policy Gradient: A Simple Efficient Policy Optimization Framework For Online RL (2023)0.00
• Provably Efficient Exploration In Policy Optimization (2019)0.00
• Conservative Dual Policy Optimization For Efficient Model-based Reinforcement Learning (2022)0.00
• Policy Optimization For Continuous Reinforcement Learning (2023)2.26
• Nearly Optimal Policy Optimization With Stable At Any Time Guarantee (2021)0.00
• Actor-critic Policy Optimization In Partially Observable Multiagent Environments (2018)0.00