We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
Value estimation is a critical component of the reinforcement learning (RL) paradigm. The question of how to effectively learn predictors fo… (see more)r value from data is one of the major problems studied by the RL community, and different approaches exploit structure in the problem domain in different ways. Model learning can make use of the rich transition structure present in sequences of observations, but this approach is usually not sensitive to the reward function. In contrast, model-free methods directly leverage the quantity of interest from the future but have to compose with a potentially weak scalar signal (an estimate of the return). In this paper we develop an approach for representation learning in RL that sits in between these two extremes: we propose to learn what to model in a way that can directly help value prediction. To this end we determine which features of the future trajectory provide useful information to predict the associated return. This provides us with tractable prediction targets that are directly relevant for a task, and can thus accelerate learning of the value function. The idea can be understood as reasoning, in hindsight, about which aspects of the future observations could help past value prediction. We show how this can help dramatically even in simple policy evaluation settings. We then test our approach at scale in challenging domains, including on 57 Atari 2600 games.
The variational autoencoder (VAE) can learn the manifold of natural images on certain datasets, as evidenced by meaningful interpolating or … (see more)extrapolating in the continuous latent space. However, on discrete data such as text, it is unclear if unsupervised learning can discover similar latent space that allows controllable manipulation. In this work, we find that sequence VAEs trained on text fail to properly decode when the latent codes are manipulated, because the modified codes often land in holes or vacant regions in the aggregated posterior latent space, where the decoding network fails to generalize. Both as a validation of the explanation and as a fix to the problem, we propose to constrain the posterior mean to a learned probability simplex, and performs manipulation within this simplex. Our proposed method mitigates the latent vacancy problem and achieves the first success in unsupervised learning of controllable representations for text. Empirically, our method outperforms unsupervised baselines and strong supervised approaches on text style transfer, and is capable of performing more flexible fine-grained control over text generation than existing methods.
The ubiquitous nature of dialogue systems and their interaction with users generate an enormous amount of data. Can we improve chatbots usin… (see more)g this data? A self-feeding chatbot improves itself by asking natural language feedback when a user is dissatisfied with its response and uses this feedback as an additional training sample. However, user feedback in most cases contains extraneous sequences hindering their usefulness as a training sample. In this work, we propose a generative adversarial model that converts noisy feedback into a plausible natural response in a conversation. The generator’s goal is to convert the feedback into a response that answers the user’s previous utterance and to fool the discriminator which distinguishes feedback from natural responses. We show that augmenting original training data with these modified feedback responses improves the original chatbot performance from 69.94%to 75.96% in ranking correct responses on the PERSONACHATdataset, a large improvement given that the original model is already trained on 131k samples.
2020-01-01
Conference on Empirical Methods in Natural Language Processing (published)
There is an analogy between machine learning systems and economic entities in that they are both adaptive, and their behaviour is specified … (see more)in a more-or-less explicit way. It appears that the area of AI that is most analogous to the behaviour of economic entities is that of morally good decision-making, but it is an open question as to how precisely moral behaviour can be achieved in an AI system. This paper explores the analogy between these two complex systems, and we suggest that a clearer understanding of this apparent analogy may help us forward in both the socio-economic domain and the AI domain: known results in economics may help inform feasible solutions in AI safety, but also known results in AI may inform economic policy. If this claim is correct, then the recent successes of deep learning for AI suggest that more implicit specifications work better than explicit ones for solving such problems.
16p11.2 and 22q11.2 Copy Number Variants (CNVs) confer high risk for Autism Spectrum Disorder (ASD), schizophrenia (SZ), and Attention-Defic… (see more)it-Hyperactivity-Disorder (ADHD), but their impact on functional connectivity (FC) remains unclear. We analyzed resting-state functional magnetic resonance imaging data from 101 CNV carriers, 755 individuals with idiopathic ASD, SZ, or ADHD and 1,072 controls. We used CNV FC-signatures to identify dimensions contributing to complex idiopathic conditions. CNVs had large mirror effects on FC at the global and regional level. Thalamus, somatomotor, and posterior insula regions played a critical role in dysconnectivity shared across deletions, duplications, idiopathic ASD, SZ but not ADHD. Individuals with higher similarity to deletion FC-signatures exhibited worse cognitive and behavioral symptoms. Deletion similarities identified at the connectivity level could be related to the redundant associations observed genome-wide between gene expression spatial patterns and FC-signatures. Results may explain why many CNVs affect a similar range of neuropsychiatric symptoms.
The standard approach for modeling partially observed systems is to model them as partially observable Markov decision processes (POMDPs) an… (see more)d obtain a dynamic program in terms of a belief state. The belief state formulation works well for planning but is not ideal for online reinforcement learning because the belief state depends on the model and, as such, is not observable when the model is unknown.In this paper, we present an alternative notion of an information state for obtaining a dynamic program in partially observed models. In particular, an information state is a sufficient statistic for the current reward which evolves in a controlled Markov manner. We show that such an information state leads to a dynamic programming decomposition. Then we present a notion of an approximate information state and present an approximate dynamic program based on the approximate information state. Approximate information state is defined in terms of properties that can be estimated using sampled trajectories. Therefore, they provide a constructive method for reinforcement learning in partially observed systems. We present one such construction and show that it performs better than the state of the art for three benchmark models.
2019-12-01
IEEE Conference on Decision and Control (published)
