Robust Reinforcement Learning under model misspecification
Not on the map. Why?
Abstract (arXiv)
Reinforcement learning has achieved remarkable performance in a wide range of tasks these days. Nevertheless, some unsolved problems limit its applications in real-world control. One of them is model misspecification, a situation where an agent is trained and deployed in environments with different transition dynamics. We propose an novel framework that utilize history trajectory and Partial Observable Markov Decision Process Modeling to deal with this dilemma. Additionally, we put forward an efficient adversarial attack method to assist robust training. Our experiments in four gym domains validate the effectiveness of our framework.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 24 of its 33 references that are in the map. First posted on arXiv 29 Mar 2021.
Builds on
24 of 33 references.
References · 24
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
- 2016OpenAI Gymcited by 1,684
- 2017Reinforcement Learning with Deep Energy-Based Policiescited by 659
- 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 616
- 2017Robust Adversarial Reinforcement Learningcited by 439
- 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 342
- 2017Adversarial Attacks on Neural Network Policiescited by 314
- 2019Challenges of Real-World Reinforcement Learningcited by 282
- 2016Deep Visual Foresight for Planning Robot Motioncited by 276
- 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 270
12 more
- 2019Action Robust Reinforcement Learning and Applications in Continuous Controlcited by 167
- 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 152
- 2017Delving into adversarial attacks on deep policiescited by 104
- 2015Memory-based control with recurrent neural networkscited by 77
- 2019Robust Reinforcement Learning for Continuous Control with Model Misspecificationcited by 76
- 2019Risk Averse Robust Adversarial Reinforcement Learningcited by 54
- 2017Reinforcement Learning under Model Mismatchcited by 52
- 2019Distributionally Robust Reinforcement Learningcited by 40
- 2019Control Regularization for Reduced Variance Reinforcement Learningcited by 34
- 2018Learning Robust Optionscited by 17
- 2018Online Robust Policy Learning in the Presence of Unknown Adversariescited by 15
- 2019Adversary A3C for Robust Reinforcement Learningcited by 6
Built on by
Citing papers per year: 2022: 2.
2 papers.