Research papers and code for "Peter Henderson":
The current flood of information in all areas of machine learning research, from computer vision to reinforcement learning, has made it difficult to make aggregate scientific inferences. It can be challenging to distill a myriad of similar papers into a set of useful principles, to determine which new methodologies to use for a particular application, and to be confident that one has compared against all relevant related work when developing new ideas. However, such a rapidly growing body of research literature is a problem that other fields have already faced - in particular, medicine and epidemiology. In those fields, systematic reviews and meta-analyses have been used exactly for dealing with these issues and it is not uncommon for entire journals to be dedicated to such analyses. Here, we suggest the field of machine learning might similarly benefit from meta-analysis and systematic review, and we encourage further discussion and development along this direction.

* Accepted to the Critiquing and Correcting Trends in Machine Learning Workshop (CRACT) at NeurIPS 2018
Click to Read Paper and Get Code
Motion detection in video is important for a number of applications and fields. In video surveillance, motion detection is an essential accompaniment to activity recognition for early warning systems. Robotics also has much to gain from motion detection and segmentation, particularly in high speed motion tracking for tactile systems. There are a myriad of techniques for detecting and masking motion in an image. Successful systems have used Gaussian Models to discern background from foreground in an image (motion from static imagery). However, particularly in the case of a moving camera or frame of reference, it is necessary to compensate for the motion of the camera when attempting to discern objects moving in the foreground. For example, it is possible to estimate motion of the camera through optical flow methods or temporal differencing and then compensate for this motion in a background subtraction model. We selection a method by Yi et al. using Dual-Mode Single Gaussian Models which does just this. We implement the technique in Intel's Thread Building Blocks (TBB) and NVIDIA's CUDA libraries. We then compare parallelization improvements with a theoretical analysis of speedups based on the characteristics of our selected model and attributes of both TBB and CUDA. We make our implementation available to the public.

Click to Read Paper and Get Code
The probabilistic bisection algorithm (PBA) solves a class of stochastic root-finding problems in one dimension by successively updating a prior belief on the location of the root based on noisy responses to queries at chosen points. The responses indicate the direction of the root from the queried point, and are incorrect with a fixed probability. The fixed-probability assumption is problematic in applications, and so we extend the PBA to apply when this assumption is relaxed. The extension involves the use of a power-one test at each queried point. We explore the convergence behavior of the extended PBA, showing that it converges at a rate arbitrarily close to, but slower than, the canonical "square root" rate of stochastic approximation.

Click to Read Paper and Get Code
Decentralized receding horizon control (D-RHC) provides a mechanism for coordination in multi-agent settings without a centralized command center. However, combining a set of different goals, costs, and constraints to form an efficient optimization objective for D-RHC can be difficult. To allay this problem, we use a meta-learning process -- cost adaptation -- which generates the optimization objective for D-RHC to solve based on a set of human-generated priors (cost and constraint functions) and an auxiliary heuristic. We use this adaptive D-RHC method for control of mesh-networked swarm agents. This formulation allows a wide range of tasks to be encoded and can account for network delays, heterogeneous capabilities, and increasingly large swarms through the adaptation mechanism. We leverage the Unity3D game engine to build a simulator capable of introducing artificial networking failures and delays in the swarm. Using the simulator we validate our method on an example coordinated exploration task. We demonstrate that cost adaptation allows for more efficient and safer task completion under varying environment conditions and increasingly large swarm sizes. We release our simulator and code to the community for future work.

* Accepted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018
Click to Read Paper and Get Code
Policy gradient methods have had great success in solving continuous control tasks, yet the stochastic nature of such problems makes deterministic value estimation difficult. We propose an approach which instead estimates a distribution by fitting the value function with a Bayesian Neural Network. We optimize an $\alpha$-divergence objective with Bayesian dropout approximation to learn and estimate this distribution. We show that using the Monte Carlo posterior mean of the Bayesian value function distribution, rather than a deterministic network, improves stability and performance of policy gradient methods in continuous control MuJoCo simulations.

* Accepted to Bayesian Deep Learning Workshop at NIPS 2017
Click to Read Paper and Get Code
Policy gradient methods in reinforcement learning have become increasingly prevalent for state-of-the-art performance in continuous control tasks. Novel methods typically benchmark against a few key algorithms such as deep deterministic policy gradients and trust region policy optimization. As such, it is important to present and use consistent baselines experiments. However, this can be difficult due to general variance in the algorithms, hyper-parameter tuning, and environment stochasticity. We investigate and discuss: the significance of hyper-parameters in policy gradients for continuous control, general variance in the algorithms, and reproducibility of reported results. We provide guidelines on reporting novel results as comparisons against baseline methods such that future researchers can make informed decisions when investigating novel methods.

* Accepted to Reproducibility in Machine Learning Workshop, ICML'17
Click to Read Paper and Get Code
We analyze the problem of learning a single user's preferences in an active learning setting, sequentially and adaptively querying the user over a finite time horizon. Learning is conducted via choice-based queries, where the user selects her preferred option among a small subset of offered alternatives. These queries have been shown to be a robust and efficient way to learn an individual's preferences. We take a parametric approach and model the user's preferences through a linear classifier, using a Bayesian prior to encode our current knowledge of this classifier. The rate at which we learn depends on the alternatives offered at every time epoch. Under certain noise assumptions, we show that the Bayes-optimal policy for maximally reducing entropy of the posterior distribution of this linear classifier is a greedy policy, and that this policy achieves a linear lower bound when alternatives can be constructed from the continuum. Further, we analyze a different metric called misclassification error, proving that the performance of the optimal policy that minimizes misclassification error is bounded below by a linear function of differential entropy. Lastly, we numerically compare the greedy entropy reduction policy with a knowledge gradient policy under a number of scenarios, examining their performance under both differential entropy and misclassification error.

Click to Read Paper and Get Code
Adversarial examples can be defined as inputs to a model which induce a mistake - where the model output is different than that of an oracle, perhaps in surprising or malicious ways. Original models of adversarial attacks are primarily studied in the context of classification and computer vision tasks. While several attacks have been proposed in natural language processing (NLP) settings, they often vary in defining the parameters of an attack and what a successful attack would look like. The goal of this work is to propose a unifying model of adversarial examples suitable for NLP tasks in both generative and classification settings. We define the notion of adversarial gain: based in control theory, it is a measure of the change in the output of a system relative to the perturbation of the input (caused by the so-called adversary) presented to the learner. This definition, as we show, can be used under different feature spaces and distance conditions to determine attack or defense effectiveness across different intuitive manifolds. This notion of adversarial gain not only provides a useful way for evaluating adversaries and defenses, but can act as a building block for future work in robustness under adversaries due to its rooted nature in stability and manifold theory.

Click to Read Paper and Get Code
In reinforcement learning (RL), stochastic environments can make learning a policy difficult due to high degrees of variance. As such, variance reduction methods have been investigated in other works, such as advantage estimation and control-variates estimation. Here, we propose to learn a separate reward estimator to train the value function, to help reduce variance caused by a noisy reward signal. This results in theoretical reductions in variance in the tabular case, as well as empirical improvements in both the function approximation and tabular settings in environments where rewards are stochastic. To do so, we use a modified version of Advantage Actor Critic (A2C) on variations of Atari games.

* Accepted to the International Conference on Learning Representations (ICLR) 2018 Workshop Track
Click to Read Paper and Get Code
During the past decade, several areas of speech and language understanding have witnessed substantial breakthroughs from the use of data-driven models. In the area of dialogue systems, the trend is less obvious, and most practical systems are still built through significant engineering and expert knowledge. Nevertheless, several recent results suggest that data-driven approaches are feasible and quite promising. To facilitate research in this area, we have carried out a wide survey of publicly available datasets suitable for data-driven learning of dialogue systems. We discuss important characteristics of these datasets, how they can be used to learn diverse dialogue strategies, and their other potential uses. We also examine methods for transfer learning between datasets and the use of external knowledge. Finally, we discuss appropriate choice of evaluation metrics for the learning objective.

* 56 pages including references and appendix, 5 tables and 1 figure; Under review for the Dialogue & Discourse journal. Update: paper has been rewritten and now includes several new datasets
Click to Read Paper and Get Code
In many finite horizon episodic reinforcement learning (RL) settings, it is desirable to optimize for the undiscounted return - in settings like Atari, for instance, the goal is to collect the most points while staying alive in the long run. Yet, it may be difficult (or even intractable) mathematically to learn with this target. As such, temporal discounting is often applied to optimize over a shorter effective planning horizon. This comes at the cost of potentially biasing the optimization target away from the undiscounted goal. In settings where this bias is unacceptable - where the system must optimize for longer horizons at higher discounts - the target of the value function approximator may increase in variance leading to difficulties in learning. We present an extension of temporal difference (TD) learning, which we call TD($\Delta$), that breaks down a value function into a series of components based on the differences between value functions with smaller discount factors. The separation of a longer horizon value function into these components has useful properties in scalability and performance. We discuss these properties and show theoretic and empirical improvements over standard TD learning in certain settings.

Click to Read Paper and Get Code
Deep reinforcement learning is the combination of reinforcement learning (RL) and deep learning. This field of research has been able to solve a wide range of complex decision-making tasks that were previously out of reach for a machine. Thus, deep RL opens up many new applications in domains such as healthcare, robotics, smart grids, finance, and many more. This manuscript provides an introduction to deep reinforcement learning models, algorithms and techniques. Particular focus is on the aspects related to generalization and how deep RL can be used for practical applications. We assume the reader is familiar with basic machine learning concepts.

* Foundations and Trends in Machine Learning: Vol. 11, No. 3-4, 2018
Click to Read Paper and Get Code
In recent years, significant progress has been made in solving challenging problems across various domains using deep reinforcement learning (RL). Reproducing existing work and accurately judging the improvements offered by novel methods is vital to sustaining this progress. Unfortunately, reproducing results for state-of-the-art deep RL methods is seldom straightforward. In particular, non-determinism in standard benchmark environments, combined with variance intrinsic to the methods, can make reported results tough to interpret. Without significance metrics and tighter standardization of experimental reporting, it is difficult to determine whether improvements over the prior state-of-the-art are meaningful. In this paper, we investigate challenges posed by reproducibility, proper experimental techniques, and reporting procedures. We illustrate the variability in reported metrics and results when comparing against common baselines and suggest guidelines to make future results in deep RL more reproducible. We aim to spur discussion about how to ensure continued progress in the field by minimizing wasted effort stemming from results that are non-reproducible and easily misinterpreted.

* Accepted to the Thirthy-Second AAAI Conference On Artificial Intelligence (AAAI), 2018
Click to Read Paper and Get Code
As demand drives systems to generalize to various domains and problems, the study of multitask, transfer and lifelong learning has become an increasingly important pursuit. In discrete domains, performance on the Atari game suite has emerged as the de facto benchmark for assessing multitask learning. However, in continuous domains there is a lack of agreement on standard multitask evaluation environments which makes it difficult to compare different approaches fairly. In this work, we describe a benchmark set of tasks that we have developed in an extendable framework based on OpenAI Gym. We run a simple baseline using Trust Region Policy Optimization and release the framework publicly to be expanded and used for the systematic comparison of multitask, transfer, and lifelong learning in continuous domains.

* Accepted at Lifelong Learning: A Reinforcement Learning Approach Workshop @ ICML, Sydney, Australia, 2017
Click to Read Paper and Get Code
Current conversational systems can follow simple commands and answer basic questions, but they have difficulty maintaining coherent and open-ended conversations about specific topics. Competitions like the Conversational Intelligence (ConvAI) challenge are being organized to push the research development towards that goal. This article presents in detail the RLLChatbot that participated in the 2017 ConvAI challenge. The goal of this research is to better understand how current deep learning and reinforcement learning tools can be used to build a robust yet flexible open domain conversational agent. We provide a thorough description of how a dialog system can be built and trained from mostly public-domain datasets using an ensemble model. The first contribution of this work is a detailed description and analysis of different text generation models in addition to novel message ranking and selection methods. Moreover, a new open-source conversational dataset is presented. Training on this data significantly improves the Recall@k score of the ranking and selection mechanisms compared to our baseline model responsible for selecting the message returned at each interaction.

* 46 pages including references and appendix, 14 figures, 12 tables; Under review for the Dialogue & Discourse journal
Click to Read Paper and Get Code
Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward function can be difficult, especially for intricate tasks. Inverse reinforcement learning offers a useful paradigm to learn the underlying reward function directly from expert demonstrations. Yet in reality, the corpus of demonstrations may contain trajectories arising from a diverse set of underlying reward functions rather than a single one. Thus, in inverse reinforcement learning, it is useful to consider such a decomposition. The options framework in reinforcement learning is specifically designed to decompose policies in a similar light. We therefore extend the options framework and propose a method to simultaneously recover reward options in addition to policy options. We leverage adversarial methods to learn joint reward-policy options using only observed expert states. We show that this approach works well in both simple and complex continuous control tasks and shows significant performance increases in one-shot transfer learning.

* Accepted to the Thirthy-Second AAAI Conference On Artificial Intelligence (AAAI), 2018
Click to Read Paper and Get Code
Modern virtual personal assistants provide a convenient interface for completing daily tasks via voice commands. An important consideration for these assistants is the ability to recover from automatic speech recognition (ASR) and natural language understanding (NLU) errors. In this paper, we focus on learning robust dialog policies to recover from these errors. To this end, we develop a user simulator which interacts with the assistant through voice commands in realistic scenarios with noisy audio, and use it to learn dialog policies through deep reinforcement learning. We show that dialogs generated by our simulator are indistinguishable from human generated dialogs, as determined by human evaluators. Furthermore, preliminary experimental results show that the learned policies in noisy environments achieve the same execution success rate with fewer dialog turns compared to fixed rule-based policies.

* 1st Workshop on Conversational AI at NIPS 2017
Click to Read Paper and Get Code
The use of dialogue systems as a medium for human-machine interaction is an increasingly prevalent paradigm. A growing number of dialogue systems use conversation strategies that are learned from large datasets. There are well documented instances where interactions with these system have resulted in biased or even offensive conversations due to the data-driven training process. Here, we highlight potential ethical issues that arise in dialogue systems research, including: implicit biases in data-driven systems, the rise of adversarial examples, potential sources of privacy violations, safety concerns, special considerations for reinforcement learning systems, and reproducibility concerns. We also suggest areas stemming from these issues that deserve further investigation. Through this initial survey, we hope to spur research leading to robust, safe, and ethically sound dialogue systems.

* In Submission to the AAAI/ACM conference on Artificial Intelligence, Ethics, and Society
Click to Read Paper and Get Code
We present a robust multi-robot convoying approach that relies on visual detection of the leading agent, thus enabling target following in unstructured 3-D environments. Our method is based on the idea of tracking-by-detection, which interleaves efficient model-based object detection with temporal filtering of image-based bounding box estimation. This approach has the important advantage of mitigating tracking drift (i.e. drifting away from the target object), which is a common symptom of model-free trackers and is detrimental to sustained convoying in practice. To illustrate our solution, we collected extensive footage of an underwater robot in ocean settings, and hand-annotated its location in each frame. Based on this dataset, we present an empirical comparison of multiple tracker variants, including the use of several convolutional neural networks, both with and without recurrent connections, as well as frequency-based model-free trackers. We also demonstrate the practicality of this tracking-by-detection strategy in real-world scenarios by successfully controlling a legged underwater robot in five degrees of freedom to follow another robot's independent motion.

* Accepted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017
Click to Read Paper and Get Code