Hugo Larochelle

Mark Rowland

Will Dabney

Experience replay is central to off-policy algorithms in deep reinforcement learning (RL), but there remain significant gaps in our understa… (see more)nding. We therefore present a systematic and extensive analysis of experience replay in Q-learning methods, focusing on two fundamental properties: the replay capacity and the ratio of learning updates to experience collected (replay ratio). Our additive and ablative studies upend conventional wisdom around experience replay -- greater capacity is found to substantially increase the performance of certain algorithms, while leaving others unaffected. Counterintuitively we show that theoretically ungrounded, uncorrected n-step returns are uniquely beneficial while other techniques confer limited benefit for sifting through larger memory. Separately, by directly controlling the replay ratio we contextualize previous observations in the literature and empirically measure its importance across a variety of deep RL algorithms. Finally, we conclude by testing a set of hypotheses on the nature of these performance benefits.

2020-11-20

Proceedings of the 37th International Conference on Machine Learning (published)

proceedings.mlr.press

An Effective Anti-Aliasing Approach for Residual Networks

Cristina Vasconcelos

Vincent Dumoulin

Nicolas Roux

Ross Goroshin

Image pre-processing in the frequency domain has traditionally played a vital role in computer vision and was even part of the standard pipe… (see more)line in the early days of deep learning. However, with the advent of large datasets, many practitioners concluded that this was unnecessary due to the belief that these priors can be learned from the data itself. Frequency aliasing is a phenomenon that may occur when sub-sampling any signal, such as an image or feature map, causing distortion in the sub-sampled output. We show that we can mitigate this effect by placing non-trainable blur filters and using smooth activation functions at key locations, particularly where networks lack the capacity to learn them. These simple architectural changes lead to substantial improvements in out-of-distribution generalization on both image classification under natural corruptions on ImageNet-C [10] and few-shot learning on Meta-Dataset [17], without introducing additional trainable parameters and using the default hyper-parameters of open source codebases.

2020-11-19

ArXiv (preprint)

Algorithmic Improvements for Deep Reinforcement Learning applied to Interactive Fiction

Vishal Jain

William Fedus

Doina Precup

Bellemare Marc-Emmanuel

Text-based games are a natural challenge domain for deep reinforcement learning algorithms. Their state and action spaces are combinatoriall… (see more)y large, their reward function is sparse, and they are partially observable: the agent is informed of the consequences of its actions through textual feedback. In this paper we emphasize this latter point and consider the design of a deep reinforcement learning agent that can play from feedback alone. Our design recognizes and takes advantage of the structural characteristics of text-based games. We first propose a contextualisation mechanism, based on accumulated reward, which simplifies the learning problem and mitigates partial observability. We then study different methods that rely on the notion that most actions are ineffectual in any given situation, following Zahavy et al.'s idea of an admissible action. We evaluate these techniques in a series of text-based games of increasing difficulty based on the TextWorld framework, as well as the iconic game Zork. Empirically, we find that these techniques improve the performance of a baseline deep reinforcement learning agent applied to text-based games.

2020-04-02

Proceedings of the AAAI Conference on Artificial Intelligence (published)

On Catastrophic Interference in Atari 2600 Games

William Fedus

Dibya Ghosh

John D. Martin

Bellemare Marc-Emmanuel

Model-free deep reinforcement learning is sample inefficient. One hypothesis -- speculated, but not confirmed -- is that catastrophic interf… (see more)erence within an environment inhibits learning. We test this hypothesis through a large-scale empirical study in the Arcade Learning Environment (ALE) and, indeed, find supporting evidence. We show that interference causes performance to plateau; the network cannot train on segments beyond the plateau without degrading the policy used to reach there. By synthetically controlling for interference, we demonstrate performance boosts across architectures, learning algorithms and environments. A more refined analysis shows that learning one segment of a game often increases prediction errors elsewhere. Our study provides a clear empirical link between catastrophic interference and sample efficiency in reinforcement learning.

2020-02-27

ArXiv (preprint)

Language Gans Falling Short

Massimo Caccia

Lucas Caccia

William Fedus

Joelle Pineau

Laurent Charlin

Generating high-quality text with sufficient diversity is essential for a wide range of Natural Language Generation (NLG) tasks. Maximum-Lik… (see more)elihood (MLE) models trained with teacher forcing have consistently been reported as weak baselines, where poor performance is attributed to exposure bias (Bengio et al., 2015; Ranzato et al., 2015); at inference time, the model is fed its own prediction instead of a ground-truth token, which can lead to accumulating errors and poor samples. This line of reasoning has led to an outbreak of adversarial based approaches for NLG, on the account that GANs do not suffer from exposure bias. In this work, we make several surprising observations which contradict common beliefs. First, we revisit the canonical evaluation framework for NLG, and point out fundamental flaws with quality-only evaluation: we show that one can outperform such metrics using a simple, well-known temperature parameter to artificially reduce the entropy of the model's conditional distributions. Second, we leverage the control over the quality / diversity trade-off given by this parameter to evaluate models over the whole quality-diversity spectrum and find MLE models constantly outperform the proposed GAN variants over the whole quality-diversity space. Our results have several implications: 1) The impact of exposure bias on sample quality is less severe than previously thought, 2) temperature tuning provides a better quality / diversity trade-off than adversarial training while being easier to train, easier to cross-validate, and less computationally expensive. Code to reproduce the experiments is available at github.com/pclucas14/GansFallingShort

2019-12-31

ICLR (published)

Learning Graph Structure With A Finite-State Automaton Layer

Daniel D. Johnson

Daniel Tarlow

2019-12-31

Advances in Neural Information Processing Systems 33 (NeurIPS 2020) (published)

Small-GAN: Speeding Up GAN Training Using Core-Sets

Samarth Sinha

Han Zhang

Anirudh Goyal

Augustus Odena

Recent work by Brock et al. (2018) suggests that Generative Adversarial Networks (GANs) benefit disproportionately from large mini-batch siz… (see more)es. Unfortunately, using large batches is slow and expensive on conventional hardware. Thus, it would be nice if we could generate batches that were effectively large though actually small. In this work, we propose a method to do this, inspired by the use of Coreset-selection in active learning. When training a GAN, we draw a large batch of samples from the prior and then compress that batch using Coreset-selection. To create effectively large batches of 'real' images, we create a cached dataset of Inception activations of each training image, randomly project them down to a smaller dimension, and then use Coreset-selection on those projected activations at training time. We conduct experiments showing that this technique substantially reduces training time and memory usage for modern GAN variants, that it reduces the fraction of dropped modes in a synthetic dataset, and that it allows GANs to reach a new state of the art in anomaly detection.

2019-12-31

ICML (published)

proceedings.mlr.press

Your GAN is Secretly an Energy-based Model and You Should Use Discriminator Driven Latent Sampling

Tong Che

Ruixiang Zhang

Jascha Sohl-Dickstein

Liam Paull

Yuan Cao

We show that the sum of the implicit generator log-density …

2019-12-31

Advances in Neural Information Processing Systems 33 (NeurIPS 2020) (published)

Learning Neural Causal Models from Unknown Interventions

Nan Rosemary Ke

Christopher Pal

Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from obs… (see more)ervational data. However, there are theoretical limitations on the identifiability of underlying structures obtained from observational data alone. Interventional data provides much richer information about the underlying data-generating process. However, the extension and application of methods designed for observational data to include interventions is not straightforward and remains an open problem. In this paper we provide a general framework based on continuous optimization and neural networks to create models for the combination of observational and interventional data. The proposed method is even applicable in the challenging and realistic case that the identity of the intervened upon variable is unknown. We examine the proposed method in the setting of graph recovery both de novo and from a partially-known edge set. We establish strong benchmark results on several structure learning tasks, including structure recovery of both synthetic graphs as well as standard graphs from the Bayesian Network Repository.

2019-09-24

ArXiv (preprint)

Hyperbolic Discounting and Learning over Multiple Horizons

William Fedus

Carles Gelada

Bellemare Marc-Emmanuel

Reinforcement learning (RL) typically defines a discount factor as part of the Markov Decision Process. The discount factor values future re… (see more)wards by an exponential scheme that leads to theoretical convergence guarantees of the Bellman equation. However, evidence from psychology, economics and neuroscience suggests that humans and animals instead have hyperbolic time-preferences. In this work we revisit the fundamentals of discounting in RL and bridge this disconnect by implementing an RL agent that acts via hyperbolic discounting. We demonstrate that a simple approach approximates hyperbolic discount functions while still using familiar temporal-difference learning techniques in RL. Additionally, and independent of hyperbolic discounting, we make a surprising discovery that simultaneously learning value functions over multiple time-horizons is an effective auxiliary task which often improves over a strong value-based RL agent, Rainbow.

2019-02-18

ArXiv (preprint)

InfoBot: Structured Exploration in ReinforcementLearning Using Information Bottleneck

D. Strouse

Matthew Botvinick

Sergey Levine

2018-12-31

(published)

www.semanticscholar.org

InfoBot: Transfer and Exploration via the Information Bottleneck

Daniel Strouse

Matthew Botvinick

Sergey Levine

A central challenge in reinforcement learning is discovering effective policies for tasks where rewards are sparsely distributed. We postula… (see more)te that in the absence of useful reward signals, an effective exploration strategy should seek out {\it decision states}. These states lie at critical junctions in the state space from where the agent can transition to new, potentially unexplored regions. We propose to learn about decision states from prior experience. By training a goal-conditioned policy with an information bottleneck, we can identify decision states by examining where the model actually leverages the goal state. We find that this simple mechanism effectively identifies decision states, even in partially observed settings. In effect, the model learns the sensory cues that correlate with potential subgoals. In new environments, this model can then identify novel subgoals for further exploration, guiding the agent through a sequence of potential decision states and through new regions of the state space.

2018-12-31

ICLR.cc/2019/Conference (poster)