Role of reward shaping in object-goal navigation

TL;DR

This paper introduces a reward shaping technique for deep reinforcement learning in object-goal navigation, improving learning efficiency by gradually adjusting rewards based on proximity to the target in simulated environments.

Contribution

The paper proposes a novel reward shaping mechanism that enhances deep reinforcement learning for object-goal navigation by incorporating distance-based reward adjustments.

Findings

Improved navigation performance in AI2-THOR environment

Enhanced learning efficiency with reward shaping

Effective handling of large environments

Abstract

Deep reinforcement learning approaches have been a popular method for visual navigation tasks in the computer vision and robotics community of late. In most cases, the reward function has a binary structure, i.e., a large positive reward is provided when the agent reaches goal state, and a negative step penalty is assigned for every other state in the environment. A sparse signal like this makes the learning process challenging, specially in big environments, where a large number of sequential actions need to be taken to reach the target. We introduce a reward shaping mechanism which gradually adjusts the reward signal based on distance to the goal. Detailed experiments conducted using the AI2-THOR simulation environment demonstrate the efficacy of the proposed approach for object-goal navigation tasks.