Robust Reinforcement Learning via Adversarial training with Langevin Dynamics

02/14/2020
by   Parameswaran Kamalaruban, et al.
0

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.

READ FULL TEXT

page 18

page 19

page 20

page 21

page 24

page 26

research
02/19/2022

Robust Reinforcement Learning as a Stackelberg Game via Adaptively-Regularized Adversarial Training

Robust Reinforcement Learning (RL) focuses on improving performances und...
research
09/07/2021

Optimal Stroke Learning with Policy Gradient Approach for Robotic Table Tennis

Learning to play table tennis is a challenging task for robots, due to t...
research
05/23/2023

Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning

Training generally capable agents that perform well in unseen dynamic en...
research
05/30/2023

Solving Robust MDPs through No-Regret Dynamics

Reinforcement Learning is a powerful framework for training agents to na...
research
12/30/2021

Constraint Sampling Reinforcement Learning: Incorporating Expertise For Faster Learning

Online reinforcement learning (RL) algorithms are often difficult to dep...
research
06/12/2023

Robust Reinforcement Learning through Efficient Adversarial Herding

Although reinforcement learning (RL) is considered the gold standard for...
research
07/22/2023

Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations

Robust reinforcement learning (RL) seeks to train policies that can perf...

Please sign up or login with your details

Forgot password? Click here to reset