Adam White

Adam White, Margarita Saranti, Artur d'Avila Garcez et al.

Machine learning offers great potential for automated prediction of post-stroke symptoms and their response to rehabilitation. Major challenges for this endeavour include the very high dimensionality of neuroimaging data, the relatively small size of the datasets available for learning, and how to effectively combine neuroimaging and tabular data (e.g. demographic information and clinical characteristics). This paper evaluates several solutions based on two strategies. The first is to use 2D images that summarise MRI scans. The second is to select key features that improve classification accuracy. Additionally, we introduce the novel approach of training a convolutional neural network (CNN) on images that combine regions-of-interest extracted from MRIs, with symbolic representations of tabular data. We evaluate a series of CNN architectures (both 2D and a 3D) that are trained on different representations of MRI and tabular data, to predict whether a composite measure of post-stroke spoken picture description ability is in the aphasic or non-aphasic range. MRI and tabular data were acquired from 758 English speaking stroke survivors who participated in the PLORAS study. The classification accuracy for a baseline logistic regression was 0.678 for lesion size alone, rising to 0.757 and 0.813 when initial symptom severity and recovery time were successively added. The highest classification accuracy 0.854 was observed when 8 regions-of-interest was extracted from each MRI scan and combined with lesion size, initial severity and recovery time in a 2D Residual Neural Network.Our findings demonstrate how imaging and tabular data can be combined for high post-stroke classification accuracy, even when the dataset is small in machine learning terms. We conclude by proposing how the current models could be improved to achieve even higher levels of accuracy using images from hospital scanners.

Andrew Patterson, Samuel Neumann, Raksha Kumaraswamy et al.

This paper introduces a new empirical methodology, the Cross-environment Hyperparameter Setting Benchmark, that compares RL algorithms across environments using a single hyperparameter setting, encouraging algorithmic development which is insensitive to hyperparameters. We demonstrate that this benchmark is robust to statistical noise and obtains qualitatively similar results across repeated applications, even when using few samples. This robustness makes the benchmark computationally cheap to apply, allowing statistically sound insights at low cost. We demonstrate two example instantiations of the CHS, on a set of six small control environments (SC-CHS) and on the entire DM Control suite of 28 environments (DMC-CHS). Finally, to illustrate the applicability of the CHS to modern RL algorithms on challenging environments, we conduct a novel empirical study of an open question in the continuous control literature. We show, with high confidence, that there is no meaningful difference in performance between Ornstein-Uhlenbeck noise and uncorrelated Gaussian noise for exploration with the DDPG algorithm on the DMC-CHS.

David Rolnick, Alan Aspuru-Guzik, Sara Beery et al. · mit

As applications of machine learning proliferate, innovative algorithms inspired by specific real-world challenges have become increasingly important. Such work offers the potential for significant impact not merely in domains of application but also in machine learning itself. In this paper, we describe the paradigm of application-driven research in machine learning, contrasting it with the more standard paradigm of methods-driven research. We illustrate the benefits of application-driven machine learning and how this approach can productively synergize with methods-driven work. Despite these benefits, we find that reviewing, hiring, and teaching practices in machine learning often hold back application-driven innovation. We outline how these processes may be improved.

Muhammad Kamran Janjua, Haseeb Shah, Martha White et al.

In this paper we investigate the use of reinforcement-learning based prediction approaches for a real drinking-water treatment plant. Developing such a prediction system is a critical step on the path to optimizing and automating water treatment. Before that, there are many questions to answer about the predictability of the data, suitable neural network architectures, how to overcome partial observability and more. We first describe this dataset, and highlight challenges with seasonality, nonstationarity, partial observability, and heterogeneity across sensors and operation modes of the plant. We then describe General Value Function (GVF) predictions -- discounted cumulative sums of observations -- and highlight why they might be preferable to classical n-step predictions common in time series prediction. We discuss how to use offline data to appropriately pre-train our temporal difference learning (TD) agents that learn these GVF predictions, including how to select hyperparameters for online fine-tuning in deployment. We find that the TD-prediction agent obtains an overall lower normalized mean-squared error than the n-step prediction agent. Finally, we show the importance of learning in deployment, by comparing a TD agent trained purely offline with no online updating to a TD agent that learns online. This final result is one of the first to motivate the importance of adapting predictions in real-time, for non-stationary high-volume systems in the real world.

Golnaz Mesbahi, Parham Mohammad Panahi, Olya Mastikhina et al.

In continual RL we want agents capable of never-ending learning, and yet our evaluation methodologies do not reflect this. The standard practice in RL is to assume unfettered access to the deployment environment for the full lifetime of the agent. For example, agent designers select the best performing hyperparameters in Atari by testing each for 200 million frames and then reporting results on 200 million frames. In this position paper, we argue and demonstrate the pitfalls of this inappropriate empirical methodology: lifetime tuning. We provide empirical evidence to support our position by testing DQN and SAC across several of continuing and non-stationary environments with two main findings: (1) lifetime tuning does not allow us to identify algorithms that work well for continual learning -- all algorithms equally succeed; (2) recently developed continual RL algorithms outperform standard non-continual algorithms when tuning is limited to a fraction of the agent's lifetime. The goal of this paper is to provide an explanation for why recent progress in continual RL has been mixed and motivate the development of empirical practices that better match the goals of continual RL.

Kevin Roice, Parham Mohammad Panahi, Scott M. Jordan et al.

This paper investigates a new approach to model-based reinforcement learning using background planning: mixing (approximate) dynamic programming updates and model-free updates, similar to the Dyna architecture. Background planning with learned models is often worse than model-free alternatives, such as Double DQN, even though the former uses significantly more memory and computation. The fundamental problem is that learned models can be inaccurate and often generate invalid states, especially when iterated many steps. In this paper, we avoid this limitation by constraining background planning to a set of (abstract) subgoals and learning only local, subgoal-conditioned models. This goal-space planning (GSP) approach is more computationally efficient, naturally incorporates temporal abstraction for faster long-horizon planning and avoids learning the transition dynamics entirely. We show that our GSP algorithm can propagate value from an abstract space in a manner that helps a variety of base learners learn significantly faster in different domains.

Adam White, Artur d'Avila Garcez

In many applications, it is important to be able to explain the decisions of machine learning systems. An increasingly popular approach has been to seek to provide \emph{counterfactual instance explanations}. These specify close possible worlds in which, contrary to the facts, a person receives their desired decision from the machine learning system. This paper will draw on literature from the philosophy of science to argue that a satisfactory explanation must consist of both counterfactual instances and a causal equation (or system of equations) that support the counterfactual instances. We will show that counterfactual instances by themselves explain little. We will further illustrate how explainable AI methods that provide both causal equations and counterfactual instances can successfully explain machine learning predictions.

Ray Jiang, Tom Zahavy, Zhongwen Xu et al.

Off-policy learning allows us to learn about possible policies of behavior from experience generated by a different behavior policy. Temporal difference (TD) learning algorithms can become unstable when combined with function approximation and off-policy sampling - this is known as the ''deadly triad''. Emphatic temporal difference (ETD($λ$)) algorithm ensures convergence in the linear case by appropriately weighting the TD($λ$) updates. In this paper, we extend the use of emphatic methods to deep reinforcement learning agents. We show that naively adapting ETD($λ$) to popular deep reinforcement learning algorithms, which use forward view multi-step returns, results in poor performance. We then derive new emphatic algorithms for use in the context of such algorithms, and we demonstrate that they provide noticeable benefits in small problems designed to highlight the instability of TD methods. Finally, we observed improved performance when applying these algorithms at scale on classic Atari games from the Arcade Learning Environment.

Vincent Liu, Adam White, Hengshuai Yao et al.

Catastrophic interference is common in many network-based learning systems, and many proposals exist for mitigating it. But, before we overcome interference we must understand it better. In this work, we provide a definition of interference for control in reinforcement learning. We systematically evaluate our new measures, by assessing correlation with several measures of learning performance, including stability, sample efficiency, and online and offline control performance across a variety of learning architectures. Our new interference measure allows us to ask novel scientific questions about commonly used deep learning architectures. In particular we show that target network frequency is a dominating factor for interference, and that updates on the last layer result in significantly higher interference than updates internal to the network. This new measure can be expensive to compute; we conclude with motivation for an efficient proxy measure and empirically demonstrate it is correlated with our definition of interference.

Sina Ghiassian, Andrew Patterson, Shivam Garg et al.

It is still common to use Q-learning and temporal difference (TD) learning-even though they have divergence issues and sound Gradient TD alternatives exist-because divergence seems rare and they typically perform well. However, recent work with large neural network learning systems reveals that instability is more common than previously thought. Practitioners face a difficult dilemma: choose an easy to use and performant TD method, or a more complex algorithm that is more sound but harder to tune and all but unexplored with non-linear function approximation or control. In this paper, we introduce a new method called TD with Regularized Corrections (TDRC), that attempts to balance ease of use, soundness, and performance. It behaves as well as TD, when TD performs well, but is sound in cases where TD diverges. We empirically investigate TDRC across a range of problems, for both prediction and control, and for both linear and non-linear function approximation, and show, potentially for the first time, that gradient TD methods could be a better alternative to TD and Q-learning.

Sina Ghiassian, Banafsheh Rafiee, Yat Long Lo et al.

Reinforcement learning systems require good representations to work well. For decades practical success in reinforcement learning was limited to small domains. Deep reinforcement learning systems, on the other hand, are scalable, not dependent on domain specific prior knowledge and have been successfully used to play Atari, in 3D navigation from pixels, and to control high degree of freedom robots. Unfortunately, the performance of deep reinforcement learning systems is sensitive to hyper-parameter settings and architecture choices. Even well tuned systems exhibit significant instability both within a trial and across experiment replications. In practice, significant expertise and trial and error are usually required to achieve good performance. One potential source of the problem is known as catastrophic interference: when later training decreases performance by overriding previous learning. Interestingly, the powerful generalization that makes Neural Networks (NN) so effective in batch supervised learning might explain the challenges when applying them in reinforcement learning tasks. In this paper, we explore how online NN training and interference interact in reinforcement learning. We find that simply re-mapping the input observations to a high-dimensional space improves learning speed and parameter sensitivity. We also show this preprocessing reduces interference in prediction tasks. More practically, we provide a simple approach to NN training that is easy to implement, and requires little additional computation. We demonstrate that our approach improves performance in both prediction and control with an extensive batch of experiments in classic control domains.

Adam White, Artur d'Avila Garcez

We propose a novel method for explaining the predictions of any classifier. In our approach, local explanations are expected to explain both the outcome of a prediction and how that prediction would change if 'things had been different'. Furthermore, we argue that satisfactory explanations cannot be dissociated from a notion and measure of fidelity, as advocated in the early days of neural networks' knowledge extraction. We introduce a definition of fidelity to the underlying classifier for local explanation models which is based on distances to a target decision boundary. A system called CLEAR: Counterfactual Local Explanations via Regression, is introduced and evaluated. CLEAR generates w-counterfactual explanations that state minimum changes necessary to flip a prediction's classification. CLEAR then builds local regression models, using the w-counterfactuals to measure and improve the fidelity of its regressions. By contrast, the popular LIME method, which also uses regression to generate local explanations, neither measures its own fidelity nor generates counterfactuals. CLEAR's regressions are found to have significantly higher fidelity than LIME's, averaging over 45% higher in this paper's four case studies.

Andrew Jacobsen, Matthew Schlegel, Cameron Linke et al.

This paper investigates different vector step-size adaptation approaches for non-stationary online, continual prediction problems. Vanilla stochastic gradient descent can be considerably improved by scaling the update with a vector of appropriately chosen step-sizes. Many methods, including AdaGrad, RMSProp, and AMSGrad, keep statistics about the learning process to approximate a second order update---a vector approximation of the inverse Hessian. Another family of approaches use meta-gradient descent to adapt the step-size parameters to minimize prediction error. These meta-descent strategies are promising for non-stationary problems, but have not been as extensively explored as quasi-second order methods. We first derive a general, incremental meta-descent algorithm, called AdaGain, designed to be applicable to a much broader range of algorithms, including those with semi-gradient updates or even those with accelerations, such as RMSProp. We provide an empirical comparison of methods from both families. We conclude that methods from both families can perform well, but in non-stationary prediction problems the meta-descent methods exhibit advantages. Our method is particularly robust across several prediction problems, and is competitive with the state-of-the-art method on a large-scale, time-series prediction problem on real data from a mobile robot.

Cam Linke, Nadia M. Ady, Martha White et al.

Learning about many things can provide numerous benefits to a reinforcement learning system. For example, learning many auxiliary value functions, in addition to optimizing the environmental reward, appears to improve both exploration and representation learning. The question we tackle in this paper is how to sculpt the stream of experience---how to adapt the learning system's behavior---to optimize the learning of a collection of value functions. A simple answer is to compute an intrinsic reward based on the statistics of each auxiliary learner, and use reinforcement learning to maximize that intrinsic reward. Unfortunately, implementing this simple idea has proven difficult, and thus has been the focus of decades of study. It remains unclear which of the many possible measures of learning would work well in a parallel learning setting where environmental reward is extremely sparse or absent. In this paper, we investigate and compare different intrinsic reward mechanisms in a new bandit-like parallel-learning testbed. We discuss the interaction between reward and prediction learners and highlight the importance of introspective prediction learners: those that increase their rate of learning when progress is possible, and decrease when it is not. We provide a comprehensive empirical comparison of 14 different rewards, including well-known ideas from reinforcement learning and active learning. Our results highlight a simple but seemingly powerful principle: intrinsic rewards based on the amount of learning can generate useful behavior, if each individual learner is introspective.

Yi Wan, Zaheer Abbas, Adam White et al.

Distribution and sample models are two popular model choices in model-based reinforcement learning (MBRL). However, learning these models can be intractable, particularly when the state and action spaces are large. Expectation models, on the other hand, are relatively easier to learn due to their compactness and have also been widely used for deterministic environments. For stochastic environments, it is not obvious how expectation models can be used for planning as they only partially characterize a distribution. In this paper, we propose a sound way of using approximate expectation models for MBRL. In particular, we 1) show that planning with an expectation model is equivalent to planning with a distribution model if the state value function is linear in state features, 2) analyze two common parametrization choices for approximating the expectation: linear and non-linear expectation models, 3) propose a sound model-based policy evaluation algorithm and present its convergence results, and 4) empirically demonstrate the effectiveness of the proposed planning algorithm.

Tom Schaul, Hado van Hasselt, Joseph Modayil et al.

We want to make progress toward artificial general intelligence, namely general-purpose agents that autonomously learn how to competently act in complex environments. The purpose of this report is to sketch a research outline, share some of the most important open issues we are facing, and stimulate further discussion in the community. The content is based on some of our discussions during a week-long workshop held in Barbados in February 2018.

Raksha Kumaraswamy, Matthew Schlegel, Adam White et al.

Directed exploration strategies for reinforcement learning are critical for learning an optimal policy in a minimal number of interactions with the environment. Many algorithms use optimism to direct exploration, either through visitation estimates or upper confidence bounds, as opposed to data-inefficient strategies like ε-greedy that use random, undirected exploration. Most data-efficient exploration methods require significant computation, typically relying on a learned model to guide exploration. Least-squares methods have the potential to provide some of the data-efficiency benefits of model-based approaches -- because they summarize past interactions -- with the computation closer to that of model-free approaches. In this work, we provide a novel, computationally efficient, incremental exploration strategy, leveraging this property of least-squares temporal difference learning (LSTD). We derive upper confidence bounds on the action-values learned by LSTD, with context-dependent (or state-dependent) noise variance. Such context-dependent noise focuses exploration on a subset of variable states, and allows for reduced exploration in other states. We empirically demonstrate that our algorithm can converge more quickly than other incremental exploration strategies using confidence estimates on action-values.

Matthew Schlegel, Andrew Jacobsen, Zaheer Abbas et al.

State construction is important for learning in partially observable environments. A general purpose strategy for state construction is to learn the state update using a Recurrent Neural Network (RNN), which updates the internal state using the current internal state and the most recent observation. This internal state provides a summary of the observed sequence, to facilitate accurate predictions and decision-making. At the same time, specifying and training RNNs is notoriously tricky, particularly as the common strategy to approximate gradients back in time, called truncated Back-prop Through Time (BPTT), can be sensitive to the truncation window. Further, domain-expertise--which can usually help constrain the function class and so improve trainability--can be difficult to incorporate into complex recurrent units used within RNNs. In this work, we explore how to use multi-step predictions to constrain the RNN and incorporate prior knowledge. In particular, we revisit the idea of using predictions to construct state and ask: does constraining (parts of) the state to consist of predictions about the future improve RNN trainability? We formulate a novel RNN architecture, called a General Value Function Network (GVFN), where each internal state component corresponds to a prediction about the future represented as a value function. We first provide an objective for optimizing GVFNs, and derive several algorithms to optimize this objective. We then show that GVFNs are more robust to the truncation level, in many cases only requiring one-step gradient updates.

Yangchen Pan, Muhammad Zaheer, Adam White et al.

Model-based strategies for control are critical to obtain sample efficient learning. Dyna is a planning paradigm that naturally interleaves learning and planning, by simulating one-step experience to update the action-value function. This elegant planning strategy has been mostly explored in the tabular setting. The aim of this paper is to revisit sample-based planning, in stochastic and continuous domains with learned models. We first highlight the flexibility afforded by a model over Experience Replay (ER). Replay-based methods can be seen as stochastic planning methods that repeatedly sample from a buffer of recent agent-environment interactions and perform updates to improve data efficiency. We show that a model, as opposed to a replay buffer, is particularly useful for specifying which states to sample from during planning, such as predecessor states that propagate information in reverse from a state more quickly. We introduce a semi-parametric model learning approach, called Reweighted Experience Models (REMs), that makes it simple to sample next states or predecessors. We demonstrate that REM-Dyna exhibits similar advantages over replay-based methods in learning in continuous state problems, and that the performance gap grows when moving to stochastic domains, of increasing size.

Craig Sherstan, Brendan Bennett, Kenny Young et al.

This paper investigates estimating the variance of a temporal-difference learning agent's update target. Most reinforcement learning methods use an estimate of the value function, which captures how good it is for the agent to be in a particular state and is mathematically expressed as the expected sum of discounted future rewards (called the return). These values can be straightforwardly estimated by averaging batches of returns using Monte Carlo methods. However, if we wish to update the agent's value estimates during learning--before terminal outcomes are observed--we must use a different estimation target called the λ-return, which truncates the return with the agent's own estimate of the value function. Temporal difference learning methods estimate the expected λ-return for each state, allowing these methods to update online and incrementally, and in most cases achieve better generalization error and faster learning than Monte Carlo methods. Naturally one could attempt to estimate higher-order moments of the λ-return. This paper is about estimating the variance of the λ-return. Prior work has shown that given estimates of the variance of the λ-return, learning systems can be constructed to (1) mitigate risk in action selection, and (2) automatically adapt the parameters of the learning process itself to improve performance. Unfortunately, existing methods for estimating the variance of the λ-return are complex and not well understood empirically. We contribute a method for estimating the variance of the λ-return directly using policy evaluation methods from reinforcement learning. Our approach is significantly simpler than prior methods that independently estimate the second moment of the λ-return. Empirically our new approach behaves at least as well as existing approaches, but is generally more robust.

Adam White, Richard S. Sutton

This document should serve as a quick reference for and guide to the implementation of linear GQ($λ$), a gradient-based off-policy temporal-difference learning algorithm. Explanation of the intuition and theory behind the algorithm are provided elsewhere (e.g., Maei & Sutton 2010, Maei 2011). If you questions or concerns about the content in this document or the attached java code please email Adam White (adam.white@ualberta.ca). The code is provided as part of the source files in the arXiv submission.

Yangchen Pan, Adam White, Martha White

The family of temporal difference (TD) methods span a spectrum from computationally frugal linear methods like TD(λ) to data efficient least squares methods. Least square methods make the best use of available data directly computing the TD solution and thus do not require tuning a typically highly sensitive learning rate parameter, but require quadratic computation and storage. Recent algorithmic developments have yielded several sub-quadratic methods that use an approximation to the least squares TD solution, but incur bias. In this paper, we propose a new family of accelerated gradient TD (ATD) methods that (1) provide similar data efficiency benefits to least-squares methods, at a fraction of the computation and storage (2) significantly reduce parameter sensitivity compared to linear TD methods, and (3) are asymptotically unbiased. We illustrate these claims with a proof of convergence in expectation and experiments on several benchmark domains and a large-scale industrial energy allocation domain.

Martha White, Adam White

One of the main obstacles to broad application of reinforcement learning methods is the parameter sensitivity of our core learning algorithms. In many large-scale applications, online computation and function approximation represent key strategies in scaling up reinforcement learning algorithms. In this setting, we have effective and reasonably well understood algorithms for adapting the learning-rate parameter, online during learning. Such meta-learning approaches can improve robustness of learning and enable specialization to current task, improving learning speed. For temporal-difference learning algorithms which we study here, there is yet another parameter, $λ$, that similarly impacts learning speed and stability in practice. Unfortunately, unlike the learning-rate parameter, $λ$ parametrizes the objective function that temporal-difference methods optimize. Different choices of $λ$ produce different fixed-point solutions, and thus adapting $λ$ online and characterizing the optimization is substantially more complex than adapting the learning-rate parameter. There are no meta-learning method for $λ$ that can achieve (1) incremental updating, (2) compatibility with function approximation, and (3) maintain stability of learning under both on and off-policy sampling. In this paper we contribute a novel objective function for optimizing $λ$ as a function of state rather than time. We derive a new incremental, linear complexity $λ$-adaption algorithm that does not require offline batch updating or access to a model of the world, and present a suite of experiments illustrating the practicality of our new algorithm in three different settings. Taken together, our contributions represent a concrete step towards black-box application of temporal-difference learning methods in real world problems.

Craig Sherstan, Adam White, Marlos C. Machado et al.

Agents of general intelligence deployed in real-world scenarios must adapt to ever-changing environmental conditions. While such adaptive agents may leverage engineered knowledge, they will require the capacity to construct and evaluate knowledge themselves from their own experience in a bottom-up, constructivist fashion. This position paper builds on the idea of encoding knowledge as temporally extended predictions through the use of general value functions. Prior work has focused on learning predictions about externally derived signals about a task or environment (e.g. battery level, joint position). Here we advocate that the agent should also predict internally generated signals regarding its own learning process - for example, an agent's confidence in its learned predictions. Finally, we suggest how such information would be beneficial in creating an introspective agent that is able to learn to make good decisions in a complex, changing world.

Adam White, Martha White

Off-policy reinforcement learning has many applications including: learning from demonstration, learning multiple goal seeking policies in parallel, and representing predictive knowledge. Recently there has been an proliferation of new policy-evaluation algorithms that fill a longstanding algorithmic void in reinforcement learning: combining robustness to off-policy sampling, function approximation, linear complexity, and temporal difference (TD) updates. This paper contains two main contributions. First, we derive two new hybrid TD policy-evaluation algorithms, which fill a gap in this collection of algorithms. Second, we perform an empirical comparison to elicit which of these new linear TD methods should be preferred in different situations, and make concrete suggestions about practical use.

Adam White, Joseph Modayil, Richard S. Sutton

We pursue a life-long learning approach to artificial intelligence that makes extensive use of reinforcement learning algorithms. We build on our prior work with general value functions (GVFs) and the Horde architecture. GVFs have been shown able to represent a wide variety of facts about the world's dynamics that may be useful to a long-lived agent (Sutton et al. 2011). We have also previously shown scaling - that thousands of on-policy GVFs can be learned accurately in real-time on a mobile robot (Modayil, White & Sutton 2011). That work was limited in that it learned about only one policy at a time, whereas the greatest potential benefits of life-long learning come from learning about many policies in parallel, as we explore in this paper. Many new challenges arise in this off-policy learning setting. To deal with convergence and efficiency challenges, we utilize the recently introduced GTD(λ) algorithm. We show that GTD(λ) with tile coding can simultaneously learn hundreds of predictions for five simple target policies while following a single random behavior policy, assessing accuracy with interspersed on-policy tests. To escape the need for the tests, which preclude further scaling, we introduce and empirically vali- date two online estimators of the off-policy objective (MSPBE). Finally, we use the more efficient of the two estimators to demonstrate off-policy learning at scale - the learning of value functions for one thousand policies in real time on a physical robot. This ability constitutes a significant step towards scaling life-long off-policy learning.