Don't Do What Doesn't Matter: Intrinsic Motivation with Action Usefulness

Abstract

Sparse rewards are double-edged training signals in reinforcement learning: easy to design but hard to optimize. Intrinsic motivation guidances have thus been developed toward alleviating the resulting exploration problem. They usually incentivize agents to look for new states through novelty signals. Yet, such methods encourage exhaustive exploration of the state space rather than focusing on the environment's salient interaction opportunities. We propose a new exploration method, called Don't Do What Doesn't Matter (DoWhaM), shifting the emphasis from state novelty to state with relevant actions. While most actions consistently change the state when used, \textit{e.g.} moving the agent, some actions are only effective in specific states, \textit{e.g.}, \emph{opening} a door, \emph{grabbing} an object. DoWhaM detects and rewards actions that seldom affect the environment. We evaluate DoWhaM on the procedurally-generated environment MiniGrid, against state-of-the-art methods and show that DoWhaM greatly reduces sample complexity.

arXiv commentAccepted at Internationnal Joint Conference on Artificial Intelligence (IJCAI'21) and Self-Supervision for Reinforcement Learning Workshop (SSL-RL @ICLR'21)

References in corpus (22)

• Continuous control with deep reinforcement learning
• Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
• IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
• VIME: Variational Information Maximizing Exploration
• Hindsight Experience Replay
• #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
• Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models
• Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning
• Go-Explore: a New Approach for Hard-Exploration Problems
• Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning
• Grounded Language Learning in a Simulated 3D World
• Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning
• Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning
• Kalman Temporal Differences
• Never Give Up: Learning Directed Exploration Strategies
• BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
• Computational Theories of Curiosity-Driven Learning
• TorchBeast: A PyTorch Platform for Distributed RL
• Scheduled Intrinsic Drive: A Hierarchical Take on Intrinsically Motivated Exploration
• BeBold: Exploration Beyond the Boundary of Explored Regions
• MULEX: Disentangling Exploitation from Exploration in Deep RL
• Show me the Way: Intrinsic Motivation from Demonstrations