Marc Gendron-Bellemare

Aaron Courville

Deep reinforcement learning (RL) algorithms are predominantly evaluated by comparing their relative performance on a large suite of tasks. M… (see more)ost published results on deep RL benchmarks compare point estimates of aggregate performance such as mean and median scores across tasks, ignoring the statistical uncertainty implied by the use of a finite number of training runs. Beginning with the Arcade Learning Environment (ALE), the shift towards computationally-demanding benchmarks has led to the practice of evaluating only a small number of runs per task, exacerbating the statistical uncertainty in point estimates. In this paper, we argue that reliable evaluation in the few run deep RL regime cannot ignore the uncertainty in results without running the risk of slowing down progress in the field. We illustrate this point using a case study on the Atari 100k benchmark, where we find substantial discrepancies between conclusions drawn from point estimates alone versus a more thorough statistical analysis. With the aim of increasing the field's confidence in reported results with a handful of runs, we advocate for reporting interval estimates of aggregate performance and propose performance profiles to account for the variability in results, as well as present more robust and efficient aggregate metrics, such as interquartile mean scores, to achieve small uncertainty in results. Using such statistical tools, we scrutinize performance evaluations of existing algorithms on other widely used RL benchmarks including the ALE, Procgen, and the DeepMind Control Suite, again revealing discrepancies in prior comparisons. Our findings call for a change in how we evaluate performance in deep RL, for which we present a more rigorous evaluation methodology, accompanied with an open-source library rliable, to prevent unreliable results from stagnating the field. This work received an outstanding paper award at NeurIPS 2021.

openreview.net

Autonomous navigation of stratospheric balloons using reinforcement learning

S. Candido

Jun Gong

Marlos C. Machado

Subhodeep Moitra

Sameera S. Ponda

Ziyun Wang

2020-12-01

Nature (published)

doi.org

A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms

Philip. Amortila

Doina Precup

Prakash Panangaden

We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We demonstrate it… (see more)s effectiveness by presenting simple and unified proofs of convergence for a variety of commonly-used methods. We show that value-based methods such as TD(

2020-03-27

ArXiv (preprint)

A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms

Philip Amortila

Doina Precup

Prakash Panangaden

2020-01-01

AISTATS (published)

proceedings.mlr.press

An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents

Felipe Petroski Such

Vashisht Madhavan

Rosanne Liu

Rui Wang

Yulun Li

Jiale Zhi

Ludwig Schubert

Jeff Clune

Joel Lehman

Much human and computational effort has aimed to improve how deep reinforcement learning (DRL) algorithms perform on benchmarks such as the … (see more)Atari Learning Environment. Comparatively less effort has focused on understanding what has been learned by such methods, and investigating and comparing the representations learned by different families of DRL algorithms. Sources of friction include the onerous computational requirements, and general logistical and architectural complications for running DRL algorithms at scale. We lessen this friction, by (1) training several algorithms at scale and releasing trained models, (2) integrating with a previous DRL model release, and (3) releasing code that makes it easy for anyone to load, visualize, and analyze such models. This paper introduces the Atari Zoo framework, which contains models trained across benchmark Atari games, in an easy-to-use format, as well as code that implements common modes of analysis and connects such models to a popular neural network visualization library. Further, to demonstrate the potential of this dataset and software package, we show initial quantitative and qualitative comparisons between the performance and representations of several DRL algorithms, highlighting interesting and previously unknown distinctions between them.

2019-08-10

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (published)

doi.org

A Comparative Analysis of Expected and Distributional Reinforcement Learning

Clare Lyle

Since their introduction a year ago, distributional approaches to reinforcement learning (distributional RL) have produced strong results re… (see more)lative to the standard approach which models expected values (expected RL). However, aside from convergence guarantees, there have been few theoretical results investigating the reasons behind the improvements distributional RL provides. In this paper we begin the investigation into this fundamental question by analyzing the differences in the tabular, linear approximation, and non-linear approximation settings. We prove that in many realizations of the tabular and linear approximation settings, distributional RL behaves exactly the same as expected RL. In cases where the two methods behave differently, distributional RL can in fact hurt performance when it does not induce identical behaviour. We then continue with an empirical analysis comparing distributional and expected RL methods in control settings with non-linear approximators to tease apart where the improvements from distributional RL methods are coming from.

2019-07-17

Proceedings of the AAAI Conference on Artificial Intelligence (published)

doi.org

The Value Function Polytope in Reinforcement Learning

Robert Dadashi

Adrien Ali Taiga

Dale Schuurmans

We establish geometric and topological properties of the space of value functions in finite state-action Markov decision processes. Our main… (see more) 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.

2019-05-24

Proceedings of the 36th International Conference on Machine Learning (published)

proceedings.mlr.press

Distributional reinforcement learning with linear function approximation

Subhodeep Moitra

Despite many algorithmic advances, our theoretical understanding of practical distributional reinforcement learning methods remains limited.… (see more) One exception is Rowland et al. (2018)'s analysis of the C51 algorithm in terms of the Cramer distance, but their results only apply to the tabular setting and ignore C51's use of a softmax to produce normalized distributions. In this paper we adapt the Cramer distance to deal with arbitrary vectors. From it we derive a new distributional algorithm which is fully Cramer-based and can be combined to linear function approximation, with formal guarantees in the context of policy evaluation. In allowing the model's prediction to be any real vector, we lose the probabilistic interpretation behind the method, but otherwise maintain the appealing properties of distributional approaches. To the best of our knowledge, ours is the first proof of convergence of a distributional algorithm combined with function approximation. Perhaps surprisingly, our results provide evidence that Cramer-based distributional methods may perform worse than directly approximating the value function.

2019-04-11

Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics (published)

proceedings.mlr.press

Distributional reinforcement learning with linear function approximation

Subhodeep Moitra

Despite many algorithmic advances, our theoretical understanding of practical distributional reinforcement learning methods remains limited.… (see more) One exception is Rowland et al. (2018)'s analysis of the C51 algorithm in terms of the Cramer distance, but their results only apply to the tabular setting and ignore C51's use of a softmax to produce normalized distributions. In this paper we adapt the Cramer distance to deal with arbitrary vectors. From it we derive a new distributional algorithm which is fully Cramer-based and can be combined to linear function approximation, with formal guarantees in the context of policy evaluation. In allowing the model's prediction to be any real vector, we lose the probabilistic interpretation behind the method, but otherwise maintain the appealing properties of distributional approaches. To the best of our knowledge, ours is the first proof of convergence of a distributional algorithm combined with function approximation. Perhaps surprisingly, our results provide evidence that Cramer-based distributional methods may perform worse than directly approximating the value function.

2019-02-08

ArXiv (preprint)

Distributional reinforcement learning with linear function approximation

Subhodeep Moitra

Despite many algorithmic advances, our theoretical understanding of practical distributional reinforcement learning methods remains limited.… (see more) One exception is Rowland et al. (2018)'s analysis of the C51 algorithm in terms of the Cramer distance, but their results only apply to the tabular setting and ignore C51's use of a softmax to produce normalized distributions. In this paper we adapt the Cramer distance to deal with arbitrary vectors. From it we derive a new distributional algorithm which is fully Cramer-based and can be combined to linear function approximation, with formal guarantees in the context of policy evaluation. In allowing the model's prediction to be any real vector, we lose the probabilistic interpretation behind the method, but otherwise maintain the appealing properties of distributional approaches. To the best of our knowledge, ours is the first proof of convergence of a distributional algorithm combined with function approximation. Perhaps surprisingly, our results provide evidence that Cramer-based distributional methods may perform worse than directly approximating the value function.

2019-02-08

ArXiv (preprint)

A Geometric Perspective on Optimal Representations for Reinforcement Learning

Will Dabney

Robert Dadashi

Adrien Ali Taiga

Dale Eric. Schuurmans

Tor Lattimore

Clare Lyle

We propose a new perspective on representation learning in reinforcement learning based on geometric properties of the space of value functi… (see more)ons. 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.

2019-01-31

ArXiv (preprint)