Robust Reinforcement Learning

By Jun Morimoto, Kenji Doya. 2005

460 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Control and Systems Engineering, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

In Control and Systems Engineering

In Reinforcement Learning

Citations in the corpus

Deep learning in neural networks: An overview (2014, background): “Many variants of traditional RL exist (e.g., Barto et al., 1983; Watkins, 1989; Watkins and Dayan, 1992; Moore and Atkeson, 1993; Schwartz, 1993; Baird, 1994; Rummery and Niranjan, 1994; Singh, 1994; Baird, 1995; Kaelbling et al., 1995; Peng and Williams, 1996; Mahadevan, 1996; Tsitsiklis and van Ro”
Fairness in Reinforcement Learning (2016, background): “The set of observations and hence the actions taken on both MDPs are identical until L reaches state sn.”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, methodology): “The parameters or weights of C are trained to maximize reward by a standard RL method such as Q-learning or similar methods [17, 292, 293, 172, 254, 212, 262, 10, 122, 188, 157, 281, 26, 216, 197, 272, 311, 9, 163, 174, 22, 27, 2, 137, 276, 156, 284].”
Robust Deep Reinforcement Learning with Adversarial Attacks (2017, methodology): “Morimoto and Doya [2005] and Pinto et al. [2017] took an indirect approach where instead of sampling worst trajectory from rollout, they employ an adversary which applies control action and tries to push the RL agent into possible bad states.”
Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning (2021, methodology): “In (100), Robust RL (RRL) implements an Actor-DisturberCritic architecture.”
Robust Multi-Agent Reinforcement Learning via Minimax Deep Deterministic Policy Gradient (2019, methodology): “Robust reinforcement learning was originally introduced by Morimoto et al. (2005) considering the generalization ability of the learned policy in the single-agent setting.”
Self-Supervised Learning in Remote Sensing: A review (2022, background): “In fact, numerous alternatives to vanilla supervised learning have been studied, such as unsupervised learning [3], semi-supervised learning [4], weakly supervised learning [5] and meta-learning [6].”
When MAML Can Adapt Fast and How to Assist When It Cannot (2019, background): “Meta-learning or learning to learn has been an appealing idea for addressing several important challenges in machine learning (Schmidhuber, 1987; Bengio et al., 1991; Vanschoren, 2019; Finn et al., 2017).”
Taking Human out of Learning Applications: A Survey on Automated Machine Learning (2018, methodology): “In this survey we focus on the usage of existing techniques in AutoML, for individual reviews on related topics please refer to [23], [24], [25] for meta-learning, [26] for transfer learning, [27] for hyperparameter optimization and [28] for neural architecture search.”
Robust Adversarial Reinforcement Learning (2017, methodology): “This formulation was introduced as robust RL (RRL) in (Morimoto & Doya, 2005).”