paper-with-me

Papers

Robust Reinforcement Learning with Distributional Risk-averse formulation

2022-06-14 · Pierre Clavier, Stéphanie Allassonière, Erwan Le Pennec

Robust Reinforcement Learning tries to make predictions more robust to changes in the dynamics or rewards of the system. This problem is particularly important when the dynamics and rewards of the environment are estimated from the data. In this paper, we approximate the Robust Reinforcement Learning constrained with a $\Phi$-divergence using an approximate Risk-Averse formulation. We show that the classical Reinforcement Learning formulation can be robustified using standard deviation penalization of the objective. Two algorithms based on Distributional Reinforcement Learning, one for discrete and one for continuous action spaces are proposed and tested in a classical Gym environment to demonstrate the robustness of the algorithms.

📄 PDF Abstract BibTeX arXiv:2206.06841

Code (0)

등록된 구현이 없습니다.

Tasks

Distributional Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning

2023-09-21 · NeurIPS 2023 11

Many real-world domains require safe decision making in uncertain environments. In this work, we introduce a deep reinforcement learning framework for approaching this important problem. We consider a distribution over t…

Improving Robustness via Risk Averse Distributional Reinforcement Learning

2020-05-01 · L4DC 2020 6 · Rahul Singh, Qinsheng Zhang, Yongxin Chen

One major obstacle that precludes the success of reinforcement learning in real-world applications is the lack of robustness, either to model uncertainties or external disturbances, of the trained policies. Robustness is…

Distributional Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Distributional Method for Risk Averse Reinforcement Learning

2023-02-27 · Ziteng Cheng, Sebastian Jaimungal, Nick Martin

We introduce a distributional method for learning the optimal policy in risk averse Markov decision process with finite state action spaces, latent costs, and stationary dynamics. We assume sequential observations of sta…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Risk-averse policies for natural gas futures trading using distributional reinforcement learning

2025-01-08 · Félicien Hêche, Biagio Nigro, Oussama Barakat, Stephan Robert-Nicoud

Financial markets have experienced significant instabilities in recent years, creating unique challenges for trading and increasing interest in risk-averse strategies. Distributional Reinforcement Learning (RL) algorithm…

Distributional Reinforcement Learningenergy tradingquantile regressionReinforcement Learning (RL)

Risk-Averse Offline Reinforcement Learning

2021-02-10 · ICLR 2021 1 · Núria Armengol Urpí, Sebastian Curi, Andreas Krause

Training Reinforcement Learning (RL) agents in high-stakes applications might be too prohibitive due to the risk associated to exploration. Thus, the agent can only use data previously collected by safe policies. While p…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)