Guttenberg, Nicholas, Yen Yu, and Ryota Kanai. “Counterfactual control for free from generative models.” arXiv preprint arXiv:1702.06676 (2017).
URL1 URL2
We introduce a method by which a generative model learning the joint distribution between actions and future states can be used to automatically infer a control scheme for any desired reward function, which may be altered on the fly without retraining the model. In this method, the problem of action selection is reduced to one of gradient descent on the latent space of the generative model, with the model itself providing the means of evaluating outcomes and finding the gradient, much like how the reward network in Deep Q-Networks (DQN) provides gradient information for the action generator. Unlike DQN or Actor-Critic, which are conditional models for a specific reward, using a generative model of the full joint distribution permits the reward to be changed on the fly. In addition, the generated futures can be inspected to gain insight in to what the network ‘thinks’ will happen, and to what went wrong when the outcomes deviate from prediction.