Learning action effects in partially observable domains

We investigate the problem of learning action effects in partially observable STRIPS planning domains. Our approach is based on a voted kernel perceptron learning model, where action and state information is encoded in a compact vector representation as input to the learning mechanism, and resulting state changes are produced as output. Our approach relies on deictic features that assume an attentional mechanism that reduces the size of the representation. We evaluate our approach on a number of partially observable planning domains, and show that it can quickly learn the dynamics of such domains, with low average error rates. We show that our approach handles noisy domains, conditional effects, and that it scales independently of the number of objects in a domain.