Robust Reinforcement Learning via Adversarial training with Langevin Dynamics
We introduce a sampling perspective to tackle the challenging task of training robust Reinforcement Learning (RL) agents. Leveraging the powerful Stochastic Gradient Langevin Dynamics, we present a novel, scalable two-player RL algorithm, which is a sampling variant of the two-player policy gradient method. Our algorithm consistently outperforms existing baselines, in terms of generalization across different training and testing conditions, on several MuJoCo environments. Our experiments also show that, even for objective functions that entirely ignore potential environmental shifts, our sampling approach remains highly robust in comparison to standard RL algorithms.
Robust RL.pdf
Preprint
openaccess
1.42 MB
Adobe PDF
e3be0aa52297c173ae3b819158d6fff9
RL_Langevin.pdf
Postprint
openaccess
n/a
2.3 MB
Adobe PDF
5916c10bf8648f46fa0b31411550a2ad