Parameter learning for POMDP spoken dialogue models

The partially observable Markov decision process (POMDP) provides a popular framework for modelling spoken dialogue. This paper describes how the expectation propagation algorithm (EP) can be used to learn the parameters of the POMDP user model. Various special probability factors applicable to this task are presented, which allow the parameters be to learned when the structure of the dialogue is complex. No annotations, neither the true dialogue state nor the true semantics of user utterances, are required. Parameters optimised using the proposed techniques are shown to improve the performance of both offline transcription experiments as well as simulated dialogue management performance. ©2010 IEEE.

Natural actor and belief critic: Reinforcement algorithm for learning parameters of dialogue systems modelled as POMDPs

This article presents a novel algorithm for learning parameters in statistical dialogue systems which are modeled as Partially Observable Markov Decision Processes (POMDPs). The three main components of a POMDP dialogue manager are a dialogue model representing dialogue state information; a policy that selects the system's responses based on the inferred state; and a reward function that specifies the desired behavior of the system. Ideally both the model parameters and the policy would be designed to maximize the cumulative reward. However, while there are many techniques available for learning the optimal policy, no good ways of learning the optimal model parameters that scale to real-world dialogue systems have been found yet. The presented algorithm, called the Natural Actor and Belief Critic (NABC), is a policy gradient method that offers a solution to this problem. Based on observed rewards, the algorithm estimates the natural gradient of the expected cumulative reward. The resulting gradient is then used to adapt both the prior distribution of the dialogue model parameters and the policy parameters. In addition, the article presents a variant of the NABC algorithm, called the Natural Belief Critic (NBC), which assumes that the policy is fixed and only the model parameters need to be estimated. The algorithms are evaluated on a spoken dialogue system in the tourist information domain. The experiments show that model parameters estimated to maximize the expected cumulative reward result in significantly improved performance compared to the baseline hand-crafted model parameters. The algorithms are also compared to optimization techniques using plain gradients and state-of-the-art random search algorithms. In all cases, the algorithms based on the natural gradient work significantly better. © 2011 ACM.

Learning feedforward commands to muscles using time-shifted sensory feedback

In adapting to changing forces in the mechanical environment, humans change the force being applied by the limb by reciprocal changes in the activation of antagonistic muscles. However, they also cocontract these muscles when interaction with the environment is mechanically unstable to increase the mechanical impedance of the limb. We have postulated that appropriate patterns of muscle activation could be learned using a simple scheme in which the naturally occurring stretch reflex is used as a template to adjust feedforward commands to muscles. Feedforward commands are modified iteratively by shifting a scaled version of the reflex response forward in time and adding it to the previous feedforward command. We show that such an algorithm can account for the principal features of changes in muscle activation observed when human subjects adapt to instabilities in the mechanical environment. © 2006.

Model based learning of sigma points in unscented Kalman filtering

The unscented Kalman filter (UKF) is a widely used method in control and time series applications. The UKF suffers from arbitrary parameters necessary for sigma point placement, potentially causing it to perform poorly in nonlinear problems. We show how to treat sigma point placement in a UKF as a learning problem in a model based view. We demonstrate that learning to place the sigma points correctly from data can make sigma point collapse much less likely. Learning can result in a significant increase in predictive performance over default settings of the parameters in the UKF and other filters designed to avoid the problems of the UKF, such as the GP-ADF. At the same time, we maintain a lower computational complexity than the other methods. We call our method UKF-L. © 2011 Elsevier B.V.

Reinforcement learning for parameter estimation in statistical spoken dialogue systems

Reinforcement techniques have been successfully used to maximise the expected cumulative reward of statistical dialogue systems. Typically, reinforcement learning is used to estimate the parameters of a dialogue policy which selects the system's responses based on the inferred dialogue state. However, the inference of the dialogue state itself depends on a dialogue model which describes the expected behaviour of a user when interacting with the system. Ideally the parameters of this dialogue model should be also optimised to maximise the expected cumulative reward. This article presents two novel reinforcement algorithms for learning the parameters of a dialogue model. First, the Natural Belief Critic algorithm is designed to optimise the model parameters while the policy is kept fixed. This algorithm is suitable, for example, in systems using a handcrafted policy, perhaps prescribed by other design considerations. Second, the Natural Actor and Belief Critic algorithm jointly optimises both the model and the policy parameters. The algorithms are evaluated on a statistical dialogue system modelled as a Partially Observable Markov Decision Process in a tourist information domain. The evaluation is performed with a user simulator and with real users. The experiments indicate that model parameters estimated to maximise the expected reward function provide improved performance compared to the baseline handcrafted parameters. © 2011 Elsevier Ltd. All rights reserved.

Phrase-based statistical language generation using graphical models and active learning

Most previous work on trainable language generation has focused on two paradigms: (a) using a statistical model to rank a set of generated utterances, or (b) using statistics to inform the generation decision process. Both approaches rely on the existence of a handcrafted generator, which limits their scalability to new domains. This paper presents BAGEL, a statistical language generator which uses dynamic Bayesian networks to learn from semantically-aligned data produced by 42 untrained annotators. A human evaluation shows that BAGEL can generate natural and informative utterances from unseen inputs in the information presentation domain. Additionally, generation performance on sparse datasets is improved significantly by using certainty-based active learning, yielding ratings close to the human gold standard with a fraction of the data. © 2010 Association for Computational Linguistics.

Dopamine and performance in a reinforcement learning task: evidence from Parkinson's disease.

The role dopamine plays in decision-making has important theoretical, empirical and clinical implications. Here, we examined its precise contribution by exploiting the lesion deficit model afforded by Parkinson's disease. We studied patients in a two-stage reinforcement learning task, while they were ON and OFF dopamine replacement medication. Contrary to expectation, we found that dopaminergic drug state (ON or OFF) did not impact learning. Instead, the critical factor was drug state during the performance phase, with patients ON medication choosing correctly significantly more frequently than those OFF medication. This effect was independent of drug state during initial learning and appears to reflect a facilitation of generalization for learnt information. This inference is bolstered by our observation that neural activity in nucleus accumbens and ventromedial prefrontal cortex, measured during simultaneously acquired functional magnetic resonance imaging, represented learnt stimulus values during performance. This effect was expressed solely during the ON state with activity in these regions correlating with better performance. Our data indicate that dopamine modulation of nucleus accumbens and ventromedial prefrontal cortex exerts a specific effect on choice behaviour distinct from pure learning. The findings are in keeping with the substantial other evidence that certain aspects of learning are unaffected by dopamine lesions or depletion, and that dopamine plays a key role in performance that may be distinct from its role in learning.

Altruistic learning.

The origin of altruism remains one of the most enduring puzzles of human behaviour. Indeed, true altruism is often thought either not to exist, or to arise merely as a miscalculation of otherwise selfish behaviour. In this paper, we argue that altruism emerges directly from the way in which distinct human decision-making systems learn about rewards. Using insights provided by neurobiological accounts of human decision-making, we suggest that reinforcement learning in game-theoretic social interactions (habitisation over either individuals or games) and observational learning (either imitative of inference based) lead to altruistic behaviour. This arises not only as a result of computational efficiency in the face of processing complexity, but as a direct consequence of optimal inference in the face of uncertainty. Critically, we argue that the fact that evolutionary pressure acts not over the object of learning ('what' is learned), but over the learning systems themselves ('how' things are learned), enables the evolution of altruism despite the direct threat posed by free-riders.

Opponent appetitive-aversive neural processes underlie predictive learning of pain relief.

Termination of a painful or unpleasant event can be rewarding. However, whether the brain treats relief in a similar way as it treats natural reward is unclear, and the neural processes that underlie its representation as a motivational goal remain poorly understood. We used fMRI (functional magnetic resonance imaging) to investigate how humans learn to generate expectations of pain relief. Using a pavlovian conditioning procedure, we show that subjects experiencing prolonged experimentally induced pain can be conditioned to predict pain relief. This proceeds in a manner consistent with contemporary reward-learning theory (average reward/loss reinforcement learning), reflected by neural activity in the amygdala and midbrain. Furthermore, these reward-like learning signals are mirrored by opposite aversion-like signals in lateral orbitofrontal cortex and anterior cingulate cortex. This dual coding has parallels to 'opponent process' theories in psychology and promotes a formal account of prediction and expectation during pain.