Reinforcement Learning Generalization with Surprise Minimization
arXiv:2004.12399
Abstract
Generalization remains a challenging problem for deep reinforcement learning algorithms, which are often trained and tested on the same set of deterministic game environments. When test environments are unseen and perturbed but the nature of the task remains the same, generalization gaps can arise. In this work, we propose and evaluate a surprise minimizing agent on a generalization benchmark to show an additional reward learned from a simple density model can show robustness in procedurally generated game environments that provide constant source of entropy and stochasticity.
arXiv commentInductive biases, invariances and generalization in RL Workshop, ICML 2020
References in corpus (10)
- Auto-Encoding Variational Bayes
- Soft Actor-Critic Algorithms and Applications
- Dota 2 with Large Scale Deep Reinforcement Learning
- IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
- A Study on Overfitting in Deep Reinforcement Learning
- Quantifying Generalization in Reinforcement Learning
- Leveraging Procedural Generation to Benchmark Reinforcement Learning
- Generalization and Regularization in DQN
- Gotta Learn Fast: A New Benchmark for Generalization in RL
- Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation