paper-with-me

Papers

Conservative Optimistic Policy Optimization via Multiple Importance Sampling

2021-03-04 · Achraf Azize, Othman Gaizi

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.

📄 PDF Abstract BibTeX arXiv:2103.03307

Code (1)

WolfLo/optimist 공식 구현 tf

Tasks

Atari GamesGame of Goreinforcement-learningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation

2023-12-24 · Paul Daoudi, Mathias Formoso, Othman Gaizi, Achraf Azize 외

A precondition for the deployment of a Reinforcement Learning agent to a real-world system is to provide guarantees on the learning process. While a learning algorithm will eventually converge to a good policy, there are…

Provably Good Batch Reinforcement Learning Without Great Exploration

2020-07-16 · Yao Liu, Adith Swaminathan, Alekh Agarwal, Emma Brunskill

Batch reinforcement learning (RL) is important to apply RL algorithms to many high stakes tasks. Doing batch RL in a way that yields a reliable new policy in large domains is challenging: a new decision policy may visit …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL

2023-10-11 · Xiyao Wang, Ruijie Zheng, Yanchao Sun, Ruonan Jia 외

Dyna-style model-based reinforcement learning contains two phases: model rollouts to generate sample for policy learning and real environment exploration using current policy for dynamics model learning. However, due to …

continuous-controlContinuous ControlModel-based Reinforcement LearningModel Predictive Control

Model-Based Offline Reinforcement Learning with Adversarial Data Augmentation

2025-03-26 · Hongye Cao, Fan Feng, Jing Huo, Shangdong Yang 외

Model-based offline Reinforcement Learning (RL) constructs environment models from offline datasets to perform conservative policy optimization. Existing approaches focus on learning state transitions through ensemble mo…

D4RLData AugmentationOffline RLreinforcement-learning+2

Policy Optimization as Online Learning with Mediator Feedback

2020-12-15 · Alberto Maria Metelli, Matteo Papini, Pierluca D'Oro, Marcello Restelli

Policy Optimization (PO) is a widely used approach to address continuous control tasks. In this paper, we introduce the notion of mediator feedback that frames PO as an online learning problem over the policy space. The …

continuous-controlContinuous Control