Author name cluster

Khimya Khetarpal

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

17 papers

2 author rows

JMLR Journal 2025 Journal Article

Optimizing Return Distributions with Distributional Dynamic Programming

Bernardo Ávila Pires
Mark Rowland
Diana Borsa
Zhaohan Daniel Guo
Khimya Khetarpal
André Barreto
David Abel
Rémi Munos

We introduce distributional dynamic programming (DP) methods for optimizing statistical functionals of the return distribution, with standard reinforcement learning as a special case. Previous distributional DP methods could optimize the same class of expected utilities as classic DP. To go beyond, we combine distributional DP with stock augmentation, a technique previously introduced for classic DP in the context of risk-sensitive RL, where the MDP state is augmented with a statistic of the rewards obtained since the first time step. We find that a number of recently studied problems can be formulated as stock-augmented return distribution optimization, and we show that we can use distributional DP to solve them. We analyze distributional value and policy iteration, with bounds and a study of what objectives these distributional DP methods can or cannot optimize. We describe a number of applications outlining how to use distributional DP to solve different stock-augmented return distribution optimization problems, for example maximizing conditional value-at-risk, and homeostatic regulation. To highlight the practical potential of stock-augmented return distribution optimization and distributional DP, we introduce an agent that combines DQN and the core ideas of distributional DP, and empirically evaluate it for solving instances of the applications discussed. [abs] [ pdf ][ bib ] &copy JMLR 2025. ( edit, beta )

PDF Details

NeurIPS Conference 2025 Conference Paper

Plasticity as the Mirror of Empowerment

David Abel
Michael Bowling
Andre Barreto
Will Dabney
Shi Dong
Steven Hansen
Anna Harutyunyan
Khimya Khetarpal

Agents are minimally entities that are influenced by their past observations and act to influence future observations. This latter capacity is captured by empowerment, which has served as a vital framing concept across artificial intelligence and cognitive science. This former capacity, however, is equally foundational: In what ways, and to what extent, can an agent be influenced by what it observes? In this paper, we ground this concept in a universal agent-centric measure that we refer to as plasticity, and reveal a fundamental connection to empowerment. Following a set of desiderata on a suitable definition, we define plasticity using a new information-theoretic quantity we call the generalized directed information. We show that this new quantity strictly generalizes the directed information introduced by Massey (1990) while preserving all of its desirable properties. Under this definition, we find that plasticity is well thought of as the mirror of empowerment: The two concepts are defined using the same measure, with only the direction of influence reversed. Our main result establishes a tension between the plasticity and empowerment of an agent, suggesting that agent design needs to be mindful of both characteristics. We explore the implications of these findings, and suggest that plasticity, empowerment, and their relationship are essential to understanding agency.

PDF Details

NeurIPS Conference 2024 Conference Paper

Balancing Context Length and Mixing Times for Reinforcement Learning at Scale

Matthew Riemer
Khimya Khetarpal
Janarthanan Rajendran
Sarath Chandar

Due to the recent remarkable advances in artificial intelligence, researchers have begun to consider challenging learning problems such as learning to generalize behavior from large offline datasets or learning online in non-Markovian environments. Meanwhile, recent advances in both of these areas have increasingly relied on conditioning policies on large context lengths. A natural question is if there is a limit to the performance benefits of increasing the context length if the computation needed is available. In this work, we establish a novel theoretical result that links the context length of a policy to the time needed to reliably evaluate its performance (i. e. , its mixing time) in large scale partially observable reinforcement learning environments that exhibit latent sub-task structure. This analysis underscores a key tradeoff: when we extend the context length, our policy can more effectively model non-Markovian dependencies, but this comes at the cost of potentially slower policy evaluation and as a result slower downstream learning. Moreover, our empirical results highlight the relevance of this analysis when leveraging Transformer based neural networks. This perspective will become increasingly pertinent as the field scales towards larger and more realistic environments, opening up a number of potential future directions for improving the way we design learning agents.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Normalization and effective learning rates in reinforcement learning

Clare Lyle
Zeyu Zheng
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 several 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 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.

PDF Details DOI

ICML Conference 2023 Conference Paper

Discovering Object-Centric Generalized Value Functions From Pixels

Somjit Nath
Gopeshh Raaj Subbaraj
Khimya Khetarpal
Samira Ebrahimi Kahou

Deep Reinforcement Learning has shown significant progress in extracting useful representations from high-dimensional inputs albeit using hand-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.

Details

TMLR Journal 2023 Journal Article

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

Khimya Khetarpal
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 with 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 relatedness 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.

PDF Details

JAIR Journal 2022 Journal Article

Towards Continual Reinforcement Learning: A Review and Perspectives

Khimya Khetarpal
Matthew Riemer
Irina Rish
Doina Precup

In this article, we aim to provide a literature review of different formulations and approaches to continual reinforcement learning (RL), also known as lifelong or non-stationary RL. We begin by discussing our perspective on why RL is a natural fit for studying continual learning. We then provide a taxonomy of different continual RL formulations by mathematically characterizing two key properties of non-stationarity, namely, the scope and driver non-stationarity. This offers a unified view of various formulations. Next, we review and present a taxonomy of continual RL approaches. We go on to discuss evaluation of continual RL agents, providing an overview of benchmarks used in the literature and important metrics for understanding agent performance. Finally, we highlight open problems and challenges in bridging the gap between the current state of continual RL and findings in neuroscience. While still in its early days, the study of continual RL has the promise to develop better incremental reinforcement learners that can function in increasingly realistic applications where non-stationarity plays a vital role. These include applications such as those in the fields of healthcare, education, logistics, and robotics.

PDF Details DOI

ICLR Conference 2021 Conference Paper

Learning Robust State Abstractions for Hidden-Parameter Block MDPs

Amy Zhang 0001
Shagun Sodhani
Khimya Khetarpal
Joelle Pineau

Many control tasks exhibit similar dynamics that can be modeled as having common latent structure. Hidden-Parameter Markov Decision Processes (HiP-MDPs) explicitly model this structure to improve sample efficiency in multi-task settings. However, this setting makes strong assumptions on the observability of the state that limit its application in real-world scenarios with rich observation spaces. In this work, we leverage ideas of common structure from the HiP-MDP setting, and extend it to enable robust state abstractions inspired by Block MDPs. We derive instantiations of this new framework for both multi-task reinforcement learning (MTRL) and meta-reinforcement learning (Meta-RL) settings. Further, we provide transfer and generalization bounds based on task and state similarity, along with sample complexity bounds that depend on the aggregate number of samples across tasks, rather than the number of tasks, a significant improvement over prior work. To further demonstrate efficacy of the proposed method, we empirically compare and show improvement over multi-task and meta-reinforcement learning baselines.

Details

KER Journal 2021 Journal Article

Safe option-critic: learning safety in the option-critic architecture

Arushi Jain
Khimya Khetarpal
Doina Precup

Abstract Designing hierarchical reinforcement learning algorithms that exhibit safe behaviour is not only vital for practical applications but also facilitates a better understanding of an agent’s decisions. We tackle this problem in the options framework (Sutton, Precup & Singh, 1999), a particular way to specify temporally abstract actions which allow an agent to use sub-policies with start and end conditions. We consider a behaviour as safe that avoids regions of state space with high uncertainty in the outcomes of actions. We propose an optimization objective that learns safe options by encouraging the agent to visit states with higher behavioural consistency. The proposed objective results in a trade-off between maximizing the standard expected return and minimizing the effect of model uncertainty in the return. We propose a policy gradient algorithm to optimize the constrained objective function. We examine the quantitative and qualitative behaviours of the proposed approach in a tabular grid world, continuous-state puddle world, and three games from the Arcade Learning Environment: Ms. Pacman, Amidar, and Q*Bert. Our approach achieves a reduction in the variance of return, boosts performance in environments with intrinsic variability in the reward structure, and compares favourably both with primitive actions and with risk-neutral options.

Details DOI

AAAI Conference 2021 Conference Paper

Self-Supervised Attention-Aware Reinforcement Learning

Haiping Wu
Khimya Khetarpal
Doina Precup

Visual saliency has emerged as a major visualization tool for interpreting deep reinforcement learning (RL) agents. However, much of the existing 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.

PDF Details

NeurIPS Conference 2021 Conference Paper

Temporally Abstract Partial Models

Khimya Khetarpal
Zafarali Ahmed
Gheorghe Comanici
Doina Precup

Humans and animals have the ability to reason and make predictions about different courses of action at many time scales. In reinforcement learning, option models (Sutton, Precup & Singh, 1999; Precup, 2000) provide the framework for this kind of temporally abstract prediction and reasoning. Natural intelligent agents are also able to focus their attention on courses of action that are relevant or feasible in a given situation, sometimes termed affordable actions. In this paper, we define a notion of affordances for options, and develop temporally abstract partial option models, that take into account the fact that an option might be affordable only in certain situations. We analyze the trade-offs between estimation and approximation error in planning and learning when using such models, and identify some interesting special cases. Additionally, we empirically demonstrate the ability to learn both affordances and partial option models online resulting in improved sample efficiency and planning time in the Taxi domain.

PDF Details

AAAI Conference 2021 Conference Paper

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

Arushi Jain
Gandharv Patil
Ayush Jain
Khimya Khetarpal
Doina Precup

Reinforcement learning algorithms are typically geared towards optimizing the expected return of an agent. However, in many practical applications, low variance in the return is desired to ensure the reliability of an algorithm. In this paper, we propose on-policy and off-policy actor-critic algorithms that optimize a performance criterion involving both mean and variance in the return. Previous work uses the second moment of return to estimate the variance indirectly. Instead, we use a much simpler recently proposed direct variance estimator which updates the estimates incrementally using temporal difference methods. Using the variance-penalized criterion, we guarantee the convergence of our algorithm to locally optimal policies for finite state action Markov decision processes. We demonstrate the utility of our algorithm in tabular and continuous MuJoCo domains. Our approach not only performs on par with actor-critic and prior variance-penalization baselines in terms of expected return, but also generates trajectories which have lower variance in the return.

PDF Details

AAAI Conference 2020 Conference Paper

Options of Interest: Temporal Abstraction with Interest Functions

Khimya Khetarpal
Martin Klissarov
Maxime Chevalier-Boisvert
Pierre-Luc Bacon
Doina Precup

Temporal abstraction refers to the ability of an agent to use behaviours of controllers which act for a limited, variable amount of time. The options framework describes such behaviours as consisting of a subset of states in which they can initiate, an internal policy and a stochastic termination condition. However, much of the subsequent work on option discovery has ignored the initiation set, because of difﬁculty in learning it from data. We provide a generalization of initiation sets suitable for general function approximation, by deﬁning an interest function associated with an option. We derive a gradient-based learning algorithm for interest functions, leading to a new interest-option-critic architecture. We investigate how interest functions can be leveraged to learn interpretable and reusable temporal abstractions. We demonstrate the efﬁcacy of the proposed approach through quantitative and qualitative results, in both discrete and continuous environments.

PDF Details

ICML Conference 2020 Conference Paper

What can I do here? A Theory of Affordances in Reinforcement Learning

Khimya Khetarpal
Zafarali Ahmed
Gheorghe Comanici
David Abel
Doina Precup

Reinforcement learning algorithms usually assume that all actions are always available to an agent. However, both people and animals understand the general link between the features of their environment and the actions that are feasible. Gibson (1977) coined the term "affordances" to describe the fact that certain states enable an agent to do certain actions, in the context of embodied agents. In this paper, we develop a theory of affordances for agents who learn and plan in Markov Decision Processes. Affordances play a dual role in this case. On one hand, they allow faster planning, by reducing the number of actions available in any given situation. On the other hand, they facilitate more efficient and precise learning of transition models from data, especially when such models require function approximation. We establish these properties through theoretical results as well as illustrative examples. We also propose an approach to learn affordances and use it to estimate transition models that are simpler and generalize better.

Details

AAAI Conference 2019 Short Paper

Learning Generalized Temporal Abstractions across Both Action and Perception

Khimya Khetarpal

Learning temporal abstractions which are partial solutions to a task and could be reused for other similar or even more complicated tasks is intuitively an ingredient which can help agents to plan, learn and reason efficiently at multiple resolutions of perceptions and time. Just like humans acquire skills and build on top of already existing skills to solve more complicated tasks, AI agents should be able to learn and develop skills continually, hierarchically and incrementally over time. In my research, I aim to answer the following question: How should an agent efficiently represent, learn and use knowledge of the world in continual tasks? My work builds on the options framework, but provides novel extensions driven by this question. We introduce the notion of interest functions. Analogous to temporally extended actions, we propose learning temporally extended perception. The key idea is to learn temporal abstractions unifying both action and perception.

PDF Details

AAAI Conference 2019 Short Paper

Learning Options with Interest Functions

Khimya Khetarpal
Doina Precup

Learning temporal abstractions which are partial solutions to a task and could be reused for solving other tasks is an ingredient that can help agents to plan and learn efficiently. In this work, we tackle this problem in the options framework. We aim to autonomously learn options which are specialized in different state space regions by proposing a notion of interest functions, which generalizes initiation sets from the options framework for function approximation. We build on the option-critic framework to derive policy gradient theorems for interest functions, leading to a new interest-option-critic architecture.

PDF Details

RLDM Conference 2019 Conference Abstract

Variational State Encoding as Intrinsic Motivation in Reinforcement Learn- ing

Martin Klissarov
Riashat Islam
Khimya Khetarpal

Discovering efficient exploration strategies is a central challenge in reinforcement learning (RL), especially in the context of sparse rewards environments. We postulate that to discover such strategies, an RL agent should be able to identify surprising, and potentially useful, states where the agent encounters meaningful information that deviates from its prior beliefs of the environment. Intuitively, this approach could be understood as leveraging a measure of an agent’s surprise to guide exploration. To this end, we provide a straightforward mechanism by training a variational auto-encoder to extract the latent structure of the task. Importantly, variational auto-encoders maintain a posterior distribution over this latent structure. By measuring the difference between this distribution and the agent’s prior beliefs, we are able to identify states which potentially hold meaningful information. Leveraging this as a measure of intrinsic motivation, we empirically demonstrate that an agent can solve a series of challenging sparse reward, highly stochastic and partially observable maze tasks.

PDF Details