arXiv subjects

Dale Schuurmans

Publications and source records attributed to Dale Schuurmans.

At least 109 records · Page 6Linked to original sources

arXiv2019

Learning to Combat Compounding-Error in Model-Based Reinforcement Learning

Despite its potential to improve sample complexity versus model-free approaches, model-based reinforcement learning can fail catastrophically if the model is inaccurate. An algorithm should ideally be able to trust an imperfect model over a reasonably long planning horizon, and only rely on model-free updates when the model errors get infeasibly large. In this paper, we investigate techniques for choosing the planning horizon on a state-dependent basis, where a state's planning horizon is determined by the maximum cumulative model error around that state. We demonstrate that these state-dependent model errors can be learned with Temporal Difference methods, based on a novel approach of temporally decomposing the cumulative model errors. Experimental results show that the proposed method can successfully adapt the planning horizon to account for state-dependent model accuracy, significantly improving the efficiency of policy learning compared to model-based and model-free baselines.

cs.LG↗

arXiv2019

AlgaeDICE: Policy Gradient from Arbitrary Experience

In many real-world applications of reinforcement learning (RL), interactions with the environment are limited due to cost or feasibility. This presents a challenge to traditional RL algorithms since the max-return objective involves an expectation over on-policy samples. We introduce a new formulation of max-return optimization that allows the problem to be re-expressed by an expectation over an arbitrary behavior-agnostic and off-policy data distribution. We first derive this result by considering a regularized version of the dual max-return objective before extending our findings to unregularized objectives through the use of a Lagrangian formulation of the linear programming characterization of Q-values. We show that, if auxiliary dual variables of the objective are optimized, then the gradient of the off-policy objective is exactly the on-policy policy gradient, without any use of importance weighting. In addition to revealing the appealing theoretical properties of this approach, we also show that it delivers good practical performance.

cs.LG↗

arXiv2019

Domain Aggregation Networks for Multi-Source Domain Adaptation

In many real-world applications, we want to exploit multiple source datasets of similar tasks to learn a model for a different but related target dataset -- e.g., recognizing characters of a new font using a set of different fonts. While most recent research has considered ad-hoc combination rules to address this problem, we extend previous work on domain discrepancy minimization to develop a finite-sample generalization bound, and accordingly propose a theoretically justified optimization procedure. The algorithm we develop, Domain AggRegation Network (DARN), is able to effectively adjust the weight of each source domain during training to ensure relevant domains are given more importance for adaptation. We evaluate the proposed method on real-world sentiment analysis and digit recognition datasets and show that DARN can significantly outperform the state-of-the-art alternatives.

cs.LG↗

arXiv2019

A Geometric Perspective on Optimal Representations for Reinforcement Learning

We propose a new perspective on representation learning in reinforcement learning based on geometric properties of the space of value functions. We leverage this perspective to provide formal evidence regarding the usefulness of value functions as auxiliary tasks. Our formulation considers adapting the representation to minimize the (linear) approximation of the value function of all stationary policies for a given environment. We show that this optimization reduces to making accurate predictions regarding a special class of value functions which we call adversarial value functions (AVFs). We demonstrate that using value functions as auxiliary tasks corresponds to an expected-error relaxation of our formulation, with AVFs a natural candidate, and identify a close relationship with proto-value functions (Mahadevan, 2005). We highlight characteristics of AVFs and their usefulness as auxiliary tasks in a series of experiments on the four-room domain.

cs.LG↗

arXiv2019

Understanding the impact of entropy on policy optimization

Entropy regularization is commonly used to improve policy optimization in reinforcement learning. It is believed to help with \emph{exploration} by encouraging the selection of more stochastic policies. In this work, we analyze this claim using new visualizations of the optimization landscape based on randomly perturbing the loss function. We first show that even with access to the exact gradient, policy optimization is difficult due to the geometry of the objective function. Then, we qualitatively show that in some environments, a policy with higher entropy can make the optimization landscape smoother, thereby connecting local optima and enabling the use of larger learning rates. This paper presents new tools for understanding the optimization landscape, shows that policy entropy serves as a regularizer, and highlights the challenge of designing general-purpose policy optimization algorithms.

cs.LG↗

arXiv2019

Learning to Generalize from Sparse and Underspecified Rewards

We consider the problem of learning from sparse and underspecified rewards, where an agent receives a complex input, such as a natural language instruction, and needs to generate a complex response, such as an action sequence, while only receiving binary success-failure feedback. Such success-failure rewards are often underspecified: they do not distinguish between purposeful and accidental success. Generalization from underspecified rewards hinges on discounting spurious trajectories that attain accidental success, while learning from sparse feedback requires effective exploration. We address exploration by using a mode covering direction of KL divergence to collect a diverse set of successful trajectories, followed by a mode seeking KL divergence to train a robust policy. We propose Meta Reward Learning (MeRL) to construct an auxiliary reward function that provides more refined feedback for learning. The parameters of the auxiliary reward function are optimized with respect to the validation performance of a trained policy. The MeRL approach outperforms our alternative reward learning technique based on Bayesian Optimization, and achieves the state-of-the-art on weakly-supervised semantic parsing. It improves previous work by 1.2% and 2.4% on WikiTableQuestions and WikiSQL datasets respectively.

cs.LG↗

arXiv2019

Advantage Amplification in Slowly Evolving Latent-State Environments

Latent-state environments with long horizons, such as those faced by recommender systems, pose significant challenges for reinforcement learning (RL). In this work, we identify and analyze several key hurdles for RL in such environments, including belief state error and small action advantage. We develop a general principle of advantage amplification that can overcome these hurdles through the use of temporal abstraction. We propose several aggregation methods and prove they induce amplification in certain settings. We also bound the loss in optimality incurred by our methods in environments where latent state evolves slowly and demonstrate their performance empirically in a stylized user-modeling task.

cs.LG↗

arXiv2019

The Value Function Polytope in Reinforcement Learning

We establish geometric and topological properties of the space of value functions in finite state-action Markov decision processes. Our main contribution is the characterization of the nature of its shape: a general polytope (Aigner et al., 2010). To demonstrate this result, we exhibit several properties of the structural relationship between policies and value functions including the line theorem, which shows that the value functions of policies constrained on all but one state describe a line segment. Finally, we use this novel perspective to introduce visualizations to enhance the understanding of the dynamics of reinforcement learning algorithms.

cs.LG↗

arXiv2019

Kernel Exponential Family Estimation via Doubly Dual Embedding

We investigate penalized maximum log-likelihood estimation for exponential family distributions whose natural parameter resides in a reproducing kernel Hilbert space. Key to our approach is a novel technique, doubly dual embedding, that avoids computation of the partition function. This technique also allows the development of a flexible sampling strategy that amortizes the cost of Monte-Carlo sampling in the inference stage. The resulting estimator can be easily generalized to kernel conditional exponential families. We establish a connection between kernel exponential family estimation and MMD-GANs, revealing a new perspective for understanding GANs. Compared to the score matching based estimators, the proposed method improves both memory and time efficiency while enjoying stronger statistical properties, such as fully capturing smoothness in its statistical convergence rate while the score matching estimator appears to saturate. Finally, we show that the proposed estimator empirically outperforms state-of-the-art

cs.LG↗

arXiv2018

Smoothed Action Value Functions for Learning Gaussian Policies

State-action value functions (i.e., Q-values) are ubiquitous in reinforcement learning (RL), giving rise to popular algorithms such as SARSA and Q-learning. We propose a new notion of action value defined by a Gaussian smoothed version of the expected Q-value. We show that such smoothed Q-values still satisfy a Bellman equation, making them learnable from experience sampled from an environment. Moreover, the gradients of expected reward with respect to the mean and covariance of a parameterized Gaussian policy can be recovered from the gradient and Hessian of the smoothed Q-value function. Based on these relationships, we develop new algorithms for training a Gaussian policy directly from a learned smoothed Q-value approximator. The approach is additionally amenable to proximal optimization by augmenting the objective with a penalty on KL-divergence from a previous policy. We find that the ability to learn both a mean and covariance during training leads to significantly improved results on standard continuous control benchmarks.

cs.LG↗

arXiv2018

Variational Rejection Sampling

Learning latent variable models with stochastic variational inference is challenging when the approximate posterior is far from the true posterior, due to high variance in the gradient estimates. We propose a novel rejection sampling step that discards samples from the variational posterior which are assigned low likelihoods by the model. Our approach provides an arbitrarily accurate approximation of the true posterior at the expense of extra computation. Using a new gradient estimator for the resulting unnormalized proposal distribution, we achieve average improvements of 3.71 nats and 0.21 nats over state-of-the-art single-sample and multi-sample alternatives respectively for estimating marginal log-likelihoods using sigmoid belief networks on the MNIST dataset.

stat.ML↗

arXiv2018

Trust-PCL: An Off-Policy Trust Region Method for Continuous Control

Trust region methods, such as TRPO, are often used to stabilize policy optimization algorithms in reinforcement learning (RL). While current trust region strategies are effective for continuous control, they typically require a prohibitively large amount of on-policy interaction with the environment. To address this problem, we propose an off-policy trust region method, Trust-PCL. The algorithm is the result of observing that the optimal policy and state values of a maximum reward objective with a relative-entropy regularizer satisfy a set of multi-step pathwise consistencies along any path. Thus, Trust-PCL is able to maintain optimization stability while exploiting off-policy data to improve sample efficiency. When evaluated on a number of continuous control tasks, Trust-PCL improves the solution quality and sample efficiency of TRPO.

cs.AI↗

arXiv2017

Safe Exploration for Identifying Linear Systems via Robust Optimization

Safely exploring an unknown dynamical system is critical to the deployment of reinforcement learning (RL) in physical systems where failures may have catastrophic consequences. In scenarios where one knows little about the dynamics, diverse transition data covering relevant regions of state-action space is needed to apply either model-based or model-free RL. Motivated by the cooling of Google's data centers, we study how one can safely identify the parameters of a system model with a desired accuracy and confidence level. In particular, we focus on learning an unknown linear system with Gaussian noise assuming only that, initially, a nominal safe action is known. Define safety as satisfying specific linear constraints on the state space (e.g., requirements on process variable) that must hold over the span of an entire trajectory, and given a Probably Approximately Correct (PAC) style bound on the estimation error of model parameters, we show how to compute safe regions of action space by gradually growing a ball around the nominal safe action. One can apply any exploration strategy where actions are chosen from such safe regions. Experiments on a stylized model of data center cooling dynamics show how computing proper safe regions can increase the sample efficiency of safe exploration.

cs.LG↗

arXiv2017

Bridging the Gap Between Value and Policy Based Reinforcement Learning

We establish a new connection between value and policy based reinforcement learning (RL) based on a relationship between softmax temporal value consistency and policy optimality under entropy regularization. Specifically, we show that softmax consistent action values correspond to optimal entropy regularized policy probabilities along any action sequence, regardless of provenance. From this observation, we develop a new RL algorithm, Path Consistency Learning (PCL), that minimizes a notion of soft consistency error along multi-step action sequences extracted from both on- and off-policy traces. We examine the behavior of PCL in different scenarios and show that PCL can be interpreted as generalizing both actor-critic and Q-learning algorithms. We subsequently deepen the relationship by showing how a single model can be used to represent both a policy and the corresponding softmax state values, eliminating the need for a separate critic. The experimental evaluation demonstrates that PCL significantly outperforms strong actor-critic and Q-learning baselines across several benchmarks.

cs.AI↗

arXiv2017

Improving Policy Gradient by Exploring Under-appreciated Rewards

This paper presents a novel form of policy gradient for model-free reinforcement learning (RL) with improved exploration properties. Current policy-based methods use entropy regularization to encourage undirected exploration of the reward landscape, which is ineffective in high dimensional spaces with sparse rewards. We propose a more directed exploration strategy that promotes exploration of under-appreciated reward regions. An action sequence is considered under-appreciated if its log-probability under the current policy under-estimates its resulting reward. The proposed exploration strategy is easy to implement, requiring small modifications to an implementation of the REINFORCE algorithm. We evaluate the approach on a set of algorithmic tasks that have long challenged RL methods. Our approach reduces hyper-parameter sensitivity and demonstrates significant improvements over baseline methods. Our algorithm successfully solves a benchmark multi-digit addition task and generalizes to long sequences. This is, to our knowledge, the first time that a pure RL method has solved addition using only reward feedback.

cs.LG↗

arXiv2017

Reward Augmented Maximum Likelihood for Neural Structured Prediction

A key problem in structured output prediction is direct optimization of the task reward function that matters for test evaluation. This paper presents a simple and computationally efficient approach to incorporate task reward into a maximum likelihood framework. By establishing a link between the log-likelihood and expected reward objectives, we show that an optimal regularized expected reward is achieved when the conditional distribution of the outputs given the inputs is proportional to their exponentiated scaled rewards. Accordingly, we present a framework to smooth the predictive probability of the outputs using their corresponding rewards. We optimize the conditional log-probability of augmented outputs that are sampled proportionally to their exponentiated scaled rewards. Experiments on neural sequence to sequence models for speech recognition and machine translation show notable improvements over a maximum likelihood baseline by using reward augmented maximum likelihood (RAML), where the rewards are defined as the negative edit distance between the outputs and the ground truth labels.

cs.LG↗

arXiv2016

Stochastic Neural Networks with Monotonic Activation Functions

We propose a Laplace approximation that creates a stochastic unit from any smooth monotonic activation function, using only Gaussian noise. This paper investigates the application of this stochastic approximation in training a family of Restricted Boltzmann Machines (RBM) that are closely linked to Bregman divergences. This family, that we call exponential family RBM (Exp-RBM), is a subset of the exponential family Harmoniums that expresses family members through a choice of smooth monotonic non-linearity for each neuron. Using contrastive divergence along with our Gaussian approximation, we show that Exp-RBM can learn useful representations using novel stochastic units.

stat.ML↗

arXiv2016

Learning with a Strong Adversary

The robustness of neural networks to intended perturbations has recently attracted significant attention. In this paper, we propose a new method, \emph{learning with a strong adversary}, that learns robust classifiers from supervised data. The proposed method takes finding adversarial examples as an intermediate step. A new and simple way of finding adversarial examples is presented and experimentally shown to be efficient. Experimental results demonstrate that resulting learning method greatly improves the robustness of the classification models produced.

cs.LG↗