Imitation can be viewed as a means of enhancing learning in multiagent environments. It augments an agent's ability to learn useful behaviors by making intelligent use of the knowledge implicit in behaviors demonstrated by cooperative teachers or other more experienced agents. We propose and study a formal model of implicit imitation that can accelerate reinforcement learning dramatically in certain cases. Roughly, by observing a mentor, a reinforcement-learning agent can extract information about its own capabilities in, and the relative value of, unvisited parts of the state space. We study two specific instantiations of this model, one in which the learning agent and the mentor have identical abilities, and one designed to deal with agents and mentors with different action sets. We illustrate the benefits of implicit imitation by integrating it with prioritized sweeping, and demonstrating improved performance and convergence through observation of single and multiple mentors. Though we make some stringent assumptions regarding observability and possible interactions, we briefly comment on extensions of the model that relax these restricitions.

In TAC-00, agent designs were primarily centered around designing algorithms a tripod are sometimes bundled with the camera to solve an NPcomplete optimization and sometimes auctioned separately. However, by the second year, it for the next generation of trading agents, became common knowledge that this problem autonomous bidding in simultaneous auctions was tractable for the TAC travel game parameters. During the second year, agent designs focused Simultaneous auctions, which characterize on estimating clearing prices, and some internet sites such as eBay.com, Agent design in and substitutable goods are on offer. Complementary TAC-02, however, cannot be described so succinctly.

We show that states of a dynamical system can be usefully represented bymulti-step, action-conditional predictions of future observations. Staterepresentations that are grounded in data in this way may be easier to learn, generalize better, and be less dependent onaccurate prior models than, for example, POMDP state representations. Building on prior work by Jaeger and by Rivest and Schapire, in this paper we compare and contrast a linear specialization ofthe predictive approach with the state representations used in POMDPs and in k-order Markov models. Ours is the first specific formulation of the predictive idea that includes both stochasticity and actions (controls). We show that any system has a linear predictive state representation with number of predictions no greater than the number of states in its minimal POMDP model.

We show that states of a dynamical system can be usefully represented by multi-step, action-conditional predictions of future observations. State representations that are grounded in data in this way may be easier to learn, generalize better, and be less dependent on accurate prior models than, for example, POMDP state representations. Building on prior work by Jaeger and by Rivest and Schapire, in this paper we compare and contrast a linear specialization of the predictive approach with the state representations used in POMDPs and in k-order Markov models. Ours is the first specific formulation of the predictive idea that includes both stochasticity and actions (controls). We show that any system has a linear predictive state representation with number of predictions no greater than the number of states in its minimal POMDP model.

In previous work on "transformed mixtures of Gaussians" and "transformed hidden Markov models", we showed how the EM algorithm in a discrete latent variable model can be used to jointly normalize data (e.g., center images, pitch-normalize spectrograms) and learn a mixture model of the normalized data. The only input to the algorithm is the data, a list of possible transformations, and the number of clusters to find. The main criticism of this work was that the exhaustive computation of the posterior probabilities over transformations would make scaling up to large feature vectors and large sets of transformations intractable. Here, we describe how a tremendous speedup is acheived through the use of a variational technique for decoupling transformations, and a fast Fourier transform method for computing posterior probabilities.

Logistic units in the first hidden layer of a feedforward neural network compute the relative probability of a data point under two Gaussians. This leads us to consider substituting other density models. We present an architecture for performing discriminative learning of Hidden Markov Models using a network of many small HMM's. Experiments on speech data show it to be superior to the standard method of discriminatively training HMM's.

We describe the application of kernel methods to Natural Language Processing (NLP) problems. In many NLP tasks the objects being modeled are strings, trees, graphs or other discrete structures which require some mechanism to convert them into feature vectors. We describe kernels for various natural language structures, allowing rich, high dimensional representations of these structures. We show how a kernel over trees can be applied to parsing using the voted perceptron algorithm, and we give experimental results on the ATIS corpus of parse trees.

We consider the use of two additive control variate methods to reduce the variance of performance gradient estimates in reinforcement learning problems. The first approach we consider is the baseline method, in which a function of the current state is added to the discounted value estimate. We relate the performance of these methods, which use sample paths, to the variance of estimates based on iid data. We derive the baseline function that minimizes this variance, and we show that the variance for any baseline is the sum of the optimal variance and a weighted squared distance to the optimal baseline. We show that the widely used average discounted value baseline (where the reward is replaced by the difference between the reward and its expectation) is suboptimal.

The Temporal Coding Hypothesis of Miller and colleagues [7] suggests that animals integrate related temporal patterns of stimuli into single memory representations. We formalize this concept using quasi-Bayes estimation to update the parameters of a constrained hidden Markov model. This approach allows us to account for some surprising temporal effects in the second order conditioning experiments of Miller et al. [1, 2, 3], which other models are unable to explain.

We propose a new particle filter that incorporates a model of costs when generating particles. The approach is motivated by the observation that the costs of accidentally not tracking hypotheses might be significant in some areas of state space, and next to irrelevant in others. By incorporating a cost model into particle filtering, states that are more critical to the system performance are more likely to be tracked. Automatic calculation of the cost model is implemented using an MDP value function calculation that estimates the value of tracking a particular state. Experiments in two mobile robot domains illustrate the appropriateness of the approach.