Autonomous Reinforcement Learning

Autonomous Reinforcement Learning (ARL) focuses on enabling agents to learn and improve continuously in dynamic, real-world environments without constant human intervention or resets. Current research emphasizes developing algorithms that handle continuous learning, addressing challenges like reward shaping, efficient exploration in complex state spaces, and robustness to environmental stochasticity and hardware limitations; techniques often involve integrating vision-language models and adapting reinforcement learning algorithms for non-episodic interactions. ARL's significance lies in its potential to create more adaptable and robust AI systems for applications ranging from robotic control and autonomous driving to cybersecurity and hardware security.

Papers

November 4, 2024

So You Think You Can Scale Up Autonomous Robot Data Collection?
Suvir Mirchandani, Suneel Belkhale, Joey Hejna, Evelyn Choi, Md Sazzad Islam, Dorsa Sadigh
Reinforcement Learning Imitation Learning Robot Learning Independent Learning Robotic Data Autonomous Reinforcement Learning

June 14, 2024

DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
Hao Bai, Yifei Zhou, Mert Cemri, Jiayi Pan, Alane Suhr, Sergey Levine, Aviral Kumar
Reinforcement Learning Vision Language Model Mobile Device Effective Reinforcement Learning Digital Human Autonomous Reinforcement Learning

March 5, 2024

RACE-SM: Reinforcement Learning Based Autonomous Control for Social On-Ramp Merging
Jordan Poots
Deep Reinforcement Learning Reward Function Design Vehicle Control Autonomous Vehicle Control Autonomous Reinforcement Learning Ramp Merging

November 15, 2023

Self-Supervised Curriculum Generation for Autonomous Reinforcement Learning without Task-Specific Knowledge
Sang-Hyun Lee, Seung-Woo Seo
Reinforcement Learning Reward Function Curriculum Learning Sparse Reward Environment Task Specific Knowledge Autonomous Reinforcement Learning Adaptive Curriculum

October 31, 2023

Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback
Max Balsells, Marcel Torne, Zihan Wang, Samedh Desai, Pulkit Agrawal, Abhishek Gupta
Continual Learning Real World Reinforcement Learning Robot Experience Goal Oriented Reinforcement Learning Autonomous Reinforcement Learning

July 19, 2023

BERRY: Bit Error Robustness for Energy-Efficient Reinforcement Learning-Based Autonomous Systems
Zishen Wan, Nandhini Chandramoorthy, Karthik Swaminathan, Pin-Yu Chen, Vijay Janapa Reddi, Arijit Raychowdhury
Unmanned Aerial Vehicle Autonomous System Quality of Service Berry Picking Autonomous Reinforcement Learning Error Bit Low Voltage

May 17, 2023

Demonstration-free Autonomous Reinforcement Learning via Implicit and Bidirectional Curriculum
Jigang Kim, Daesol Cho, H. Jin Kim
Reinforcement Learning Implicit Language Independent Learning Bidirectional Learning Autonomous Reinforcement Learning

April 3, 2023

A Multiagent CyberBattleSim for RL Cyber Operation Agents
Thomas Kunz, Christian Fisher, James La Novara-Gsell, Christopher Nguyen, Li Li
Reinforcement Learning RL Agent Defense Strategy Sophisticated Agent Autonomous Reinforcement Learning

October 19, 2022

When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning
Annie Xie, Fahim Tajwar, Archit Sharma, Chelsea Finn
Reinforcement Learning HELP Request Continuous Environment Reversible Dynamic Early Intervention Autonomous Reinforcement Learning

August 29, 2022

Reinforcement Learning for Hardware Security: Opportunities, Developments, and Challenges
Satwik Patnaik, Vasudev Gohil, Hao Guo, Jeyavijayan, Rajendran
Reinforcement Learning Technical Challenge Emerging Opportunity Hardware Trojan Autonomous Reinforcement Learning Hardware Security

December 17, 2021

Autonomous Reinforcement Learning: Formalism and Benchmarking
Archit Sharma, Kelvin Xu, Nikhil Sardana, Abhishek Gupta, Karol Hausman, Sergey Levine, Chelsea Finn
Reinforcement Learning Benchmark Platform Episodic Reinforcement Learning Analysis Formalism Autonomous Reinforcement Learning

Autonomous Reinforcement Learning

Papers

So You Think You Can Scale Up Autonomous Robot Data Collection?

DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning

RACE-SM: Reinforcement Learning Based Autonomous Control for Social On-Ramp Merging

Self-Supervised Curriculum Generation for Autonomous Reinforcement Learning without Task-Specific Knowledge

Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback

BERRY: Bit Error Robustness for Energy-Efficient Reinforcement Learning-Based Autonomous Systems

Demonstration-free Autonomous Reinforcement Learning via Implicit and Bidirectional Curriculum

A Multiagent CyberBattleSim for RL Cyber Operation Agents

When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning

Reinforcement Learning for Hardware Security: Opportunities, Developments, and Challenges

Autonomous Reinforcement Learning: Formalism and Benchmarking