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.
Code (1)
Tasks
MuJoCoreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Adversarial score matching and improved sampling for image generation
Denoising Score Matching with Annealed Langevin Sampling (DSM-ALS) has recently found success in generative modeling. The approach works by first training a neural network to estimate the score of a distribution, and the…
DenoisingImage GenerationAdversarial Training Improves Joint Energy-Based Generative Modelling
We propose the novel framework for generative modelling using hybrid energy-based models. In our method we combine the interpretable input gradients of the robust classifier and Langevin Dynamics for sampling. Using the …
EBMs Trained with Maximum Likelihood are Generator Models Trained with a Self-adverserial Loss
Maximum likelihood estimation is widely used in training Energy-based models (EBMs). Training requires samples from an unnormalized distribution, which is usually intractable, and in practice, these are obtained by MCMC …
Stabilizing Training of Generative Adversarial Nets via Langevin Stein Variational Gradient Descent
Generative adversarial networks (GANs), famous for the capability of learning complex underlying data distribution, are however known to be tricky in the training process, which would probably result in mode collapse or …
DiversityVariational InferenceAdversarial Stein Training for Graph Energy Models
Learning distributions over graph-structured data is a challenging task. In this work we present an energy-based model (EBM) using graph neural networks (GNN) to learn permutation invariant unnormalized density functions…
Graph Generation