Khimya Khetarpal

James Martens

Hado van Hasselt

Razvan Pascanu

Will Dabney

Normalization layers have recently experienced a renaissance in the deep reinforcement learning and continual learning literature, with seve… (see more)ral works highlighting diverse benefits such as improving loss landscape conditioning and combatting overestimation bias. However, normalization brings with it a subtle but important side effect: an equivalence between growth in the norm of the network parameters and decay in the effective learning rate. This becomes problematic in continual learning settings, where the resulting effective learning rate schedule may decay to near zero too quickly relative to the timescale of the learning problem. We propose to make the learning rate schedule explicit with a simple re-parameterization which we call Normalize-and-Project (NaP), which couples the insertion of normalization layers with weight projection, ensuring that the effective learning rate remains constant throughout training. This technique reveals itself as a powerful analytical tool to better understand learning rate schedules in deep reinforcement learning, and as a means of improving robustness to nonstationarity in synthetic plasticity loss benchmarks along with both the single-task and sequential variants of the Arcade Learning Environment. We also show that our approach can be easily applied to popular architectures such as ResNets and transformers while recovering and in some cases even slightly improving the performance of the base model in common stationary benchmarks.

2024-07-01

ArXiv (preprint)

A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning

Zhaohan Daniel Guo

Bernardo Avila Pires

Yunhao Tang

Clare Lyle

Mark Rowland

Nicolas Heess

Diana Borsa

Arthur Guez

Will Dabney

2024-06-04

ArXiv (preprint)

Disentangling the Causes of Plasticity Loss in Neural Networks

Clare Lyle

Zeyu Zheng

Hado van Hasselt

Razvan Pascanu

James Martens

Will Dabney

2024-02-29

ArXiv (preprint)

Toward Human-AI Alignment in Large-Scale Multi-Player Games

Sugandha Sharma

Guy Davidson

Anssi Kanervisto

Udit Arora

Katja Hofmann

Ida Momennejad

Achieving human-AI alignment in complex multi-agent games is crucial for creating trustworthy AI agents that enhance gameplay. We propose a … (see more)method to evaluate this alignment using an interpretable task-sets framework, focusing on high-level behavioral tasks instead of low-level policies. Our approach has three components. First, we analyze extensive human gameplay data from Xbox's Bleeding Edge (100K+ games), uncovering behavioral patterns in a complex task space. This task space serves as a basis set for a behavior manifold capturing interpretable axes: fight-flight, explore-exploit, and solo-multi-agent. Second, we train an AI agent to play Bleeding Edge using a Generative Pretrained Causal Transformer and measure its behavior. Third, we project human and AI gameplay to the proposed behavior manifold to compare and contrast. This allows us to interpret differences in policy as higher-level behavioral concepts, e.g., we find that while human players exhibit variability in fight-flight and explore-exploit behavior, AI players tend towards uniformity. Furthermore, AI agents predominantly engage in solo play, while humans often engage in cooperative and competitive multi-agent patterns. These stark differences underscore the need for interpretable evaluation, design, and integration of AI in human-aligned applications. Our study advances the alignment discussion in AI and especially generative AI research, offering a measurable framework for interpretable human-agent alignment in multiplayer gaming.

2024-02-05

ArXiv (preprint)

Forecaster: Towards Temporally Abstract Tree-Search Planning from Pixels

Thomas Jiralerspong

Flemming Kondrup

The ability to plan at many different levels of abstraction enables agents to envision the long-term repercussions of their decisions and th… (see more)us enables sample-efficient learning. This becomes particularly beneficial in complex environments from high-dimensional state space such as pixels, where the goal is distant and the reward sparse. We introduce Forecaster, a deep hierarchical reinforcement learning approach which plans over high-level goals leveraging a temporally abstract world model. Forecaster learns an abstract model of its environment by modelling the transitions dynamics at an abstract level and training a world model on such transition. It then uses this world model to choose optimal high-level goals through a tree-search planning procedure. It additionally trains a low-level policy that learns to reach those goals. Our method not only captures building world models with longer horizons, but also, planning with such models in downstream tasks. We empirically demonstrate Forecaster's potential in both single-task learning and generalization to new tasks in the AntMaze domain.

2023-10-27

NeurIPS.cc/2023/Workshop/GenPlan (published)

POMRL: No-Regret Learning-to-Plan with Increasing Horizons

Claire Vernade

Brendan O'Donoghue

Satinder Singh

Tom Zahavy

We study the problem of planning under model uncertainty in an online meta-reinforcement learning (RL) setting where an agent is presented w… (see more)ith a sequence of related tasks with limited interactions per task. The agent can use its experience in each task and across tasks to estimate both the transition model and the distribution over tasks. We propose an algorithm to meta-learn the underlying structure across tasks, utilize it to plan in each task, and upper-bound the regret of the planning loss. Our bound suggests that the average regret over tasks decreases as the number of tasks increases and as the tasks are more similar. In the classical single-task setting, it is known that the planning horizon should depend on the estimated model's accuracy, that is, on the number of samples within task. We generalize this finding to meta-RL and study this dependence of planning horizons on the number of tasks. Based on our theoretical findings, we derive heuristics for selecting slowly increasing discount factors, and we validate its significance empirically.

2023-07-18

TMLR (accepted)

Discovering Object-Centric Generalized Value Functions From Pixels

Somjit Nath

Gopeshh Raaj Subbaraj

Samira Ebrahimi Kahou

Deep Reinforcement Learning has shown significant progress in extracting useful representations from high-dimensional inputs albeit using ha… (see more)nd-crafted auxiliary tasks and pseudo rewards. Automatically learning such representations in an object-centric manner geared towards control and fast adaptation remains an open research problem. In this paper, we introduce a method that tries to discover meaningful features from objects, translating them to temporally coherent"question"functions and leveraging the subsequent learned general value functions for control. We compare our approach with state-of-the-art techniques alongside other ablations and show competitive performance in both stationary and non-stationary settings. Finally, we also investigate the discovered general value functions and through qualitative analysis show that the learned representations are not only interpretable but also, centered around objects that are invariant to changes across tasks facilitating fast adaptation.

2023-07-03

Proceedings of the 40th International Conference on Machine Learning (published)

Towards Continual Reinforcement Learning: A Review and Perspectives

Matthew D Riemer

Irina Rish

2022-12-22

Journal of Artificial Intelligence Research (published)

The Paradox of Choice: On the Role of Attention in Hierarchical Reinforcement Learning

Andrei Cristian Nica

Decision-making AI agents are often faced with two important challenges: the depth of the planning horizon, and the branching factor due to … (see more)having many choices. Hierarchical reinforcement learning methods aim to solve the first problem, by providing shortcuts that skip over multiple time steps. To cope with the breadth, it is desirable to restrict the agent's attention at each step to a reasonable number of possible choices. The concept of affordances (Gibson, 1977) suggests that only certain actions are feasible in certain states. In this work, we first characterize "affordances" as a "hard" attention mechanism that strictly limits the available choices of temporally extended options. We then investigate the role of hard versus soft attention in training data collection, abstract value learning in long-horizon tasks, and handling a growing number of choices. To this end, we present an online, model-free algorithm to learn affordances that can be used to further learn subgoal options. Finally, we identify and empirically demonstrate the settings in which the "paradox of choice" arises, i.e. when having fewer but more meaningful choices improves the learning speed and performance of a reinforcement learning agent.

2022-10-20

NeurIPS.cc/2022/Workshop/Attention (poster)

Sequoia: A Software Framework to Unify Continual Learning Research

Fabrice Normandin

Oleksiy Ostapenko

Pau Rodriguez

Florian Golemo

Ryan Lindeborg

J. Hurtado

Matthew D Riemer

Lucas Cecchi

Timothee LESORT

Dominic Zhao

David Vazquez

Laurent Charlin

Irina Rish

Massimo Caccia

The field of Continual Learning (CL) seeks to develop algorithms that accumulate knowledge and skills over time through interaction with non… (see more)-stationary environments. In practice, a plethora of evaluation procedures (settings) and algorithmic solutions (methods) exist, each with their own potentially disjoint set of assumptions. This variety makes measuring progress in CL difficult. We propose a taxonomy of settings, where each setting is described as a set of assumptions. A tree-shaped hierarchy emerges from this view, where more general settings become the parents of those with more restrictive assumptions. This makes it possible to use inheritance to share and reuse research, as developing a method for a given setting also makes it directly applicable onto any of its children. We instantiate this idea as a publicly available software framework called Sequoia, which features a wide variety of settings from both the Continual Supervised Learning (CSL) and Continual Reinforcement Learning (CRL) domains. Sequoia also includes a growing suite of methods which are easy to extend and customize, in addition to more specialized methods from external libraries. We hope that this new paradigm and its first implementation can help unify and accelerate research in CL. You can help us grow the tree by visiting (this GitHub URL).

2021-08-02

ArXiv (preprint)

Self-Supervised Attention-Aware Reinforcement Learning

Haiping Wu

Visual saliency has emerged as a major visualization tool for interpreting deep reinforcement learning (RL) agents. However, much of the exi… (see more)sting research uses it as an analyzing tool rather than an inductive bias for policy learning. In this work, we use visual attention as an inductive bias for RL agents. We propose a novel self-supervised attention learning approach which can 1. learn to select regions of interest without explicit annotations, and 2. act as a plug for existing deep RL methods to improve the learning performance. We empirically show that the self-supervised attention-aware deep RL methods outperform the baselines in the context of both the rate of convergence and performance. Furthermore, the proposed self-supervised attention is not tied with specific policies, nor restricted to a specific scene. We posit that the proposed approach is a general self-supervised attention module for multi-task learning and transfer learning, and empirically validate the generalization ability of the proposed method. Finally, we show that our method learns meaningful object keypoints highlighting improvements both qualitatively and quantitatively.

2021-05-18

AAAI Conference on Artificial Intelligence (published)

Variance Penalized On-Policy and Off-Policy Actor-Critic

Arushi Jain

Gandharv Patil

Ayush Jain

2021-05-18

Proceedings of the AAAI Conference on Artificial Intelligence (published)