Bounded Exploration With World Model Uncertainty In Soft Actor-critic Reinforcement Learning Algorithm

Abstract

One of the bottlenecks preventing Deep Reinforcement Learning algorithms (DRL) from real-world applications is how to explore the environment and collect informative transitions efficiently. The present paper describes bounded exploration, a novel exploration method that integrates both 'soft' and intrinsic motivation exploration. Bounded exploration notably improved the Soft Actor-Critic algorithm's performance and its model-based extension's converging speed. It achieved the highest score in 6 out of 8 experiments. Bounded exploration presents an alternative method to introduce intrinsic motivations to exploration when the original reward function has strict meanings.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyqiao2024bounded

Related papers

• Efficient Exploration In Deep Reinforcement Learning: A Novel Bayesian Actor-critic Algorithm (2024)0.00
• Langevin Soft Actor-critic: Efficient Exploration Through Uncertainty-driven Critic Learning (2025)0.00
• Smart Exploration In Reinforcement Learning Using Bounded Uncertainty Models (2025)0.00
• Improving Exploration In Soft-actor-critic With Normalizing Flows Policies (2019)0.00
• Boosting Exploration In Actor-critic Algorithms By Incentivizing Plausible Novel States (2022)5.24
• Behavior-guided Actor-critic: Improving Exploration Via Learning Policy Behavior Representation For Deep Reinforcement Learning (2021)0.00
• Soft Actor-critic: Off-policy Maximum Entropy Deep Reinforcement Learning With A Stochastic Actor (2018)0.00
• Exploration In Feature Space For Reinforcement Learning (2017)0.00