Learning Approximate Stochastic Transition Models
This addresses a key bottleneck in model-based reinforcement learning for AI systems, though it is incremental as it builds on existing GAN methods.
The paper tackled the problem of learning stochastic transition models for model-based reinforcement learning that generalize to novel states, and found that a modified loss function for generative adversarial networks significantly improves performance in this task.
We examine the problem of learning mappings from state to state, suitable for use in a model-based reinforcement-learning setting, that simultaneously generalize to novel states and can capture stochastic transitions. We show that currently popular generative adversarial networks struggle to learn these stochastic transition models but a modification to their loss functions results in a powerful learning algorithm for this class of problems.