paper-with-me

Papers

Confidence-Controlled Exploration: Efficient Sparse-Reward Policy Learning for Robot Navigation

2023-06-09 · Bhrij Patel, Kasun Weerakoon, Wesley A. Suttle, Alec Koppel, Brian M. Sadler, Tianyi Zhou, Amrit Singh Bedi, Dinesh Manocha

Reinforcement learning (RL) is a promising approach for robotic navigation, allowing robots to learn through trial and error. However, real-world robotic tasks often suffer from sparse rewards, leading to inefficient exploration and suboptimal policies due to sample inefficiency of RL. In this work, we introduce Confidence-Controlled Exploration (CCE), a novel method that improves sample efficiency in RL-based robotic navigation without modifying the reward function. Unlike existing approaches, such as entropy regularization and reward shaping, which can introduce instability by altering rewards, CCE dynamically adjusts trajectory length based on policy entropy. Specifically, it shortens trajectories when uncertainty is high to enhance exploration and extends them when confidence is high to prioritize exploitation. CCE is a principled and practical solution inspired by a theoretical connection between policy entropy and gradient estimation. It integrates seamlessly with on-policy and off-policy RL methods and requires minimal modifications. We validate CCE across REINFORCE, PPO, and SAC in both simulated and real-world navigation tasks. CCE outperforms fixed-trajectory and entropy-regularized baselines, achieving an 18\% higher success rate, 20-38\% shorter paths, and 9.32\% lower elevation costs under a fixed training sample budget. Finally, we deploy CCE on a Clearpath Husky robot, demonstrating its effectiveness in complex outdoor environments.

📄 PDF Abstract BibTeX arXiv:2306.06192

Code (0)

등록된 구현이 없습니다.

Tasks

Policy Gradient Methodsreinforcement-learningReinforcement Learning (RL)Robot Navigation

Methods 이 논문이 사용한 방법론

REINFORCE REINFORCE is a Monte Carlo variant of a policy gradient algorithm in reinforcement learning. The agent collects samples of an episode using its current policy, and uses it to…

Similar Papers 제목 키워드 기반

Learning to Plan via Deep Optimistic Value Exploration

2020-06-08 · L4DC 2020 6 · Tim Seyde, Wilko Schwarting, Sertac Karaman, Daniela Rus

Deep exploration requires coordinated long-term planning. We present a model-based reinforcement learning algorithm that guides policy learning through a value function that exhibits optimism in the face of uncertainty. …

BenchmarkingModel-based Reinforcement LearningReinforcement Learning (RL)

Exploration with Foundation Models: Capabilities, Limitations, and Hybrid Approaches

2025-09-24 · Remo Sasso, Michelangelo Conserva, Dominik Jeurissen, Paulo Rauber arxiv

Exploration in reinforcement learning (RL) remains challenging, particularly in sparse-reward settings. While foundation models possess strong semantic priors, their capabilities as zero-shot exploration agents in classi…

Reinforcement LearningMulti-Armed Bandits

Skew-Explore: Learn faster in continuous spaces with sparse rewards

2019-09-25 · Xi Chen, Yuan Gao, Ali Ghadirzadeh, Marten Bjorkman 외

In many reinforcement learning settings, rewards which are extrinsically available to the learning agent are too sparse to train a suitable policy. Beside reward shaping which requires human expertise, utilizing better e…

What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning?

2025-09-04 · Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma arxiv

Sparse-reward reinforcement learning (RL) remains fundamentally hard: without structure, any agent needs $Ω(|\mathcal{S}||\mathcal{A}|/p)$ samples to recover rewards. We introduce Policy-Aware Matrix Completion (PAMC) as…

Reinforcement LearningOffline RL

Adaptive Variance for Changing Sparse-Reward Environments

2019-03-15 · Xingyu Lin, Pengsheng Guo, Carlos Florensa, David Held

Robots that are trained to perform a task in a fixed environment often fail when facing unexpected changes to the environment due to a lack of exploration. We propose a principled way to adapt the policy for better explo…