Dynamics Generalisation In Reinforcement Learning Via Adaptive Context-aware Policies

Abstract

While reinforcement learning has achieved remarkable successes in several domains, its real-world application is limited due to many methods failing to generalise to unfamiliar conditions. In this work, we consider the problem of generalising to new transition dynamics, corresponding to cases in which the environment's response to the agent's actions differs. For example, the gravitational force exerted on a robot depends on its mass and changes the robot's mobility. Consequently, in such cases, it is necessary to condition an agent's actions on extrinsic state information and pertinent contextual information reflecting how the environment responds. While the need for context-sensitive policies has been established, the manner in which context is incorporated architecturally has received less attention. Thus, in this work, we present an investigation into how context information should be incorporated into behaviour learning to improve generalisation. To this end, we introduce a neural

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keybeukman2023dynamics

Related papers

• Prototypical Context-aware Dynamics Generalization For High-dimensional Model-based Reinforcement Learning (2022)0.00
• Decomposed Mutual Information Optimization For Generalized Context In Meta-reinforcement Learning (2022)0.00
• Contextual Intelligence The Next Leap For Reinforcement Learning (2026)0.00
• Inferring Behavior-specific Context Improves Zero-shot Generalization In Reinforcement Learning (2024)0.95
• Trajectory-wise Multiple Choice Learning For Dynamics Generalization In Reinforcement Learning (2020)6.77
• Dynamics-adaptive Continual Reinforcement Learning Via Progressive Contextualization (2022)7.16
• Dynamics Generalization Via Information Bottleneck In Deep Reinforcement Learning (2020)0.00
• Learning A Subspace Of Policies For Online Adaptation In Reinforcement Learning (2021)0.00