The majority of language model training builds on imitation learning. It covers pretraining, supervised fine-tuning, and affects the starting conditions for reinforcement learning from human feedback (RLHF). The simplicity and scalability of maximum likelihood estimation (MLE) for next token prediction led to its role as predominant paradigm. However, the broader field of imitation learning can more effectively utilize the sequential structure underlying autoregressive generation. We focus on investigating the inverse reinforcement learning (IRL) perspective to imitation, extracting rewards and directly optimizing sequences instead of individual token likelihoods and evaluate its benefits for fine-tuning large language models. We provide a new angle, reformulating inverse soft-Q-learning as a temporal difference regularized extension of MLE. This creates a principled connection between MLE and IRL and allows trading off added complexity with increased performance and diversity of generations in the supervised fine-tuning (SFT) setting. We find clear advantages for IRL-based imitation, in particular for retaining diversity while maximizing task performance, rendering IRL a strong alternative on fixed SFT datasets even without online data generation. Our analysis of IRL-extracted reward functions further indicates benefits for more robust reward functions via tighter integration of supervised and preference-based LLM post-training.

Whether it's downloading applications, doing research, using communication tools, shopping online, filling out a form or finding directions, having good digital competencies is essential in our contemporary society. But what about people with cognitive limitations (PCLs)? It appears that more than 31% of PCLs do not have the basic competencies to face this new digital reality and thus function harmoniously in society. To enable them to become autonomous in activities requiring the use of the Internet via a tablet, a research and development project is underway to create TAQ-TIC, an online digital literacy learning environment adapted to their needs. Using an inclusive design approach that puts the learner at the heart of the creation process, we validated the design, usability, and pedagogical readability of TAQ-TIC with PCLs. Findings emerged that allowed us to make recommendations for online training intended for PCLs, notably the addition of navigation indicators and contextual aids, the cleaning up of screen pages both graphically and textually, and the predominant use of video-based content.

As we deploy reinforcement learning agents to solve increasingly challenging problems, methods that allow us to inject prior knowledge about the structure of the world and effective solution strategies becomes increasingly important. In this work we consider how information and architectural constraints can be combined with ideas from the probabilistic modeling literature to learn behavior priors that capture the common movement and interaction patterns that are shared across a set of related tasks or contexts. For example the day-to day behavior of humans comprises distinctive locomotion and manipulation patterns that recur across many different situations and goals. We discuss how such behavior patterns can be captured using probabilistic trajectory models and how these can be integrated effectively into reinforcement learning schemes, e.g. to facilitate multi-task and transfer learning. We then extend these ideas to latent variable models and consider a formulation to learn hierarchical priors that capture different aspects of the behavior in reusable modules. We discuss how such latent variable formulations connect to related work on hierarchical reinforcement learning (HRL) and mutual information and curiosity based objectives, thereby offering an alternative perspective on existing ideas. We demonstrate the effectiveness of our framework by applying it to a range of simulated continuous control domains, videos of which can be found at the following url: https://sites.google.com/view/behavior-priors.

An agent might be said, informally, to have mastery of its environment when it has maximised the effective number of states it can reliably reach. In practice, this often means maximizing the number of latent codes that can be discriminated from future states under some short time horizon (e.g. \cite{eysenbach2018diversity}). By situating these latent codes in a globally consistent coordinate system, we show that agents can reliably reach more states in the long term while still optimizing a local objective. A simple instantiation of this idea, \textbf{E}ntropic \textbf{D}esired \textbf{D}ynamics for \textbf{I}ntrinsic \textbf{C}on\textbf{T}rol (EDDICT), assumes fixed additive latent dynamics, which results in tractable learning and an interpretable latent space. Compared to prior methods, EDDICT's globally consistent codes allow it to be far more exploratory, as demonstrated by improved state coverage and increased unsupervised performance on hard exploration games such as Montezuma's Revenge.

Maximising a cumulative reward function that is Markov and stationary, i.e., defined over state-action pairs and independent of time, is sufficient to capture many kinds of goals in a Markov decision process (MDP). However, not all goals can be captured in this manner. In this paper we study convex MDPs in which goals are expressed as convex functions of the stationary distribution and show that they cannot be formulated using stationary reward functions. Convex MDPs generalize the standard reinforcement learning (RL) problem formulation to a larger framework that includes many supervised and unsupervised RL problems, such as apprenticeship learning, constrained MDPs, and so-called pure exploration'. Our approach is to reformulate the convex MDP problem as a min-max game involving policy and cost (negative reward)players', using Fenchel duality. We propose a meta-algorithm for solving this problem and show that it unifies many existing algorithms in the literature.

We introduce Natural Neural Networks, a novel family of algorithms that speed up convergence by adapting their internal representation during training to improve conditioning of the Fisher matrix. In particular, we show a specific example that employs a simple and efficient reparametrization of the neural network weights by implicitly whitening the representation obtained at each layer, while preserving the feed-forward computation of the network. Such networks can be trained efficiently via the proposed Projected Natural Gradient Descent algorithm (PRONG), which amortizes the cost of these reparametrizations over many parameter updates and is closely related to the Mirror Descent online learning algorithm. We highlight the benefits of our method on both unsupervised and supervised learning tasks, and showcase its scalability by training on the large-scale ImageNet Challenge dataset.

The spike-and-slab restricted Boltzmann machine (ssRBM) is defined to have both a real-valued "slab" variable and a binary "spike" variable associated with each unit in the hidden layer. The model uses its slab variables to model the conditional covariance of the observation-thought to be important in capturing the statistical properties of natural images. In this paper, we present the canonical ssRBM framework together with some extensions. These extensions highlight the flexibility of the spike-and-slab RBM as a platform for exploring more sophisticated probabilistic models of high dimensional data in general and natural image data in particular. Here, we introduce the subspace-ssRBM focused on the task of learning invariant features. We highlight the behaviour of the ssRBM and its extensions through experiments with the MNIST digit recognition task and the CIFAR-10 object classification task.

In this paper we present the techniques used for the University of Montréal's team submissions to the 2013 Emotion Recognition in the Wild Challenge. The challenge is to classify the emotions expressed by the primary human subject in short video clips extracted from feature length movies. This involves the analysis of video clips of acted scenes lasting approximately one-two seconds, including the audio track which may contain human voices as well as background music. Our approach combines multiple deep neural networks for different data modalities, including: (1) a deep convolutional neural network for the analysis of facial expressions within video frames; (2) a deep belief net to capture audio information; (3) a deep autoencoder to model the spatio-temporal information produced by the human actions depicted within the entire scene; and (4) a shallow network architecture focused on extracted features of the mouth of the primary human subject in the scene. We discuss each of these techniques, their performance characteristics and different strategies to aggregate their predictions. Our best single model was a convolutional neural network trained to predict emotions from static frames using two large data sets, the Toronto Face Database and our own set of faces images harvested from Google image search, followed by a per frame aggregation strategy that used the challenge training data. This yielded a test set accuracy of 35.58%. Using our best strategy for aggregating our top performing models into a single predictor we were able to produce an accuracy of 41.03% on the challenge test set. These compare favorably to the challenge baseline test set accuracy of 27.56%.

Markov Random Fields (MRFs) have proven very powerful both as density estimators and feature extractors for classification. However, their use is often limited by an inability to estimate the partition function $Z$. In this paper, we exploit the gradient descent training procedure of restricted Boltzmann machines (a type of MRF) to {\bf track} the log partition function during learning. Our method relies on two distinct sources of information: (1) estimating the change $\Delta Z$ incurred by each gradient update, (2) estimating the difference in $Z$ over a small set of tempered distributions using bridge sampling. The two sources of information are then combined using an inference procedure similar to Kalman filtering. Learning MRFs through Tempered Stochastic Maximum Likelihood, we can estimate $Z$ using no more temperatures than are required for learning. Comparing to both exact values and estimates using annealed importance sampling (AIS), we show on several datasets that our method is able to accurately track the log partition function. In contrast to AIS, our method provides this estimate at each time-step, at a computational cost similar to that required for training alone.