Khimya Khetarpal

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

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 (publié)

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

Arushi Jain

Abstract Designing hierarchical reinforcement learning algorithms that exhibit safe behaviour is not only vital for practical applications b… (voir plus)ut 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.

2021-04-07

The Knowledge Engineering Review (publié)

Learning Robust State Abstractions for Hidden-Parameter Block MDPs

Amy Zhang

Shagun Sodhani

Joelle Pineau

2021-01-01

ICLR (publié)

openreview.net

Temporally Abstract Partial Models

Zafarali Ahmed

Gheorghe Comanici

Humans and animals have the ability to reason and make predictions about different courses of action at many time scales. In reinforcement l… (voir plus)earning, 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.

openreview.net

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

Zafarali Ahmed

Gheorghe Comanici

David Abel

2020-11-21

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

proceedings.mlr.press

Multi-Task Reinforcement Learning as a Hidden-Parameter Block MDP

Amy Zhang

Shagun Sodhani

Joelle Pineau

Multi-task reinforcement learning is a rich paradigm where information from previously seen environments can be leveraged for better perform… (voir plus)ance and improved sample-efficiency in new environments. In this work, we leverage ideas of common structure underlying a family of Markov decision processes (MDPs) to improve performance in the few-shot regime. We use assumptions of structure from Hidden-Parameter MDPs and Block MDPs to propose a new framework, HiP-BMDP, and approach for learning a common representation and universal dynamics model. To this end, 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 demonstrate the efficacy of the proposed method, we empirically compare and show improvements against other multi-task and meta-reinforcement learning baselines.

2020-07-14

ArXiv (prépublication)

Value Preserving State-Action Abstractions

David Abel

Nathan Umbanhowar

Dilip Arumugam

Michael L. Littman

Abstraction can improve the sample efficiency of reinforcement learning. However, the process of abstraction inherently discards information… (voir plus), potentially compromising an agent’s ability to represent high-value policies. To mitigate this, we here introduce combinations of state abstractions and options that are guaranteed to preserve the representation of near-optimal policies. We first define φ-relative options, a general formalism for analyzing the value loss of options paired with a state abstraction, and present necessary and sufficient conditions for φ-relative options to preserve near-optimal behavior in any finite Markov Decision Process. We further show that, under appropriate assumptions, φ-relative options can be composed to induce hierarchical abstractions that are also guaranteed to represent high-value policies.ion can improve the sample efficiency of reinforcement learning. However, the process of abstraction inherently discards information, potentially compromising an agent’s ability to represent high-value policies. To mitigate this, we here introduce combinations of state abstractions and options that are guaranteed to preserve the representation of near-optimal policies. We first define φ-relative options, a general formalism for analyzing the value loss of options paired with a state abstraction, and present necessary and sufficient conditions for φ-relative options to preserve near-optimal behavior in any finite Markov Decision Process. We further show that, under appropriate assumptions, φ-relative options can be composed to induce hierarchical abstractions that are also guaranteed to represent high-value policies.

2020-06-03

International Conference on Artificial Intelligence and Statistics (published)

dblp.uni-trier.de

Value Preserving State-Action Abstractions

David Abel

Nathan Umbanhowar

Dilip Arumugam

Michael L. Littman

2020-06-03

International Conference on Artificial Intelligence and Statistics (publié)

proceedings.mlr.press

Options of Interest: Temporal Abstraction with Interest Functions

Martin Klissarov

Maxime Chevalier-Boisvert

Pierre-Luc Bacon

Temporal abstraction refers to the ability of an agent to use behaviours of controllers which act for a limited, variable amount of time. Th… (voir plus)e 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.

2020-04-03

Proceedings of the AAAI Conference on Artificial Intelligence (publié)

Learning Options with Interest Functions

Learning temporal abstractions which are partial solutions to a task and could be reused for solving other tasks is an ingredient that can h… (voir plus)elp 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.

2019-07-17

Proceedings of the AAAI Conference on Artificial Intelligence (publié)

Environments for Lifelong Reinforcement Learning

Shagun Sodhani

Sarath Chandar

To achieve general artificial intelligence, reinforcement learning (RL) agents should learn not only to optimize returns for one specific ta… (voir plus)sk but also to constantly build more complex skills and scaffold their knowledge about the world, without forgetting what has already been learned. In this paper, we discuss the desired characteristics of environments that can support the training and evaluation of lifelong reinforcement learning agents, review existing environments from this perspective, and propose recommendations for devising suitable environments in the future.

2018-11-26

ArXiv (prépublication)