From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learning
This work addresses a fundamental problem in reinforcement learning for agents in goal-oriented environments, offering an incremental improvement inspired by biological systems.
The paper tackles the challenge of balancing exploration and exploitation in reinforcement learning by proposing a toddler-inspired transition from sparse to dense rewards, which enhances learning performance and sample efficiency in robotic arm manipulation and 3D navigation tasks.
Reinforcement learning (RL) agents often face challenges in balancing exploration and exploitation, particularly in environments where sparse or dense rewards bias learning. Biological systems, such as human toddlers, naturally navigate this balance by transitioning from free exploration with sparse rewards to goal-directed behavior guided by increasingly dense rewards. Inspired by this natural progression, we investigate the Toddler-Inspired Reward Transition in goal-oriented RL tasks. Our study focuses on transitioning from sparse to potential-based dense (S2D) rewards while preserving optimal strategies. Through experiments on dynamic robotic arm manipulation and egocentric 3D navigation tasks, we demonstrate that effective S2D reward transitions significantly enhance learning performance and sample efficiency. Additionally, using a Cross-Density Visualizer, we show that S2D transitions smooth the policy loss landscape, resulting in wider minima that improve generalization in RL models. In addition, we reinterpret Tolman's maze experiments, underscoring the critical role of early free exploratory learning in the context of S2D rewards.