Real World Reinforcement Learning

Real-world reinforcement learning (RL) focuses on training agents to make optimal decisions directly within real-world environments, overcoming the limitations of simulation-based approaches. Current research emphasizes efficient exploration strategies, robust handling of uncertainty and non-stationarity, and techniques to reduce reliance on meticulously designed reward functions, often incorporating human feedback or pre-trained models to improve sample efficiency. This field is crucial for advancing robotics, control systems, and other applications requiring autonomous agents to learn and adapt in complex, dynamic settings, leading to improved performance and safety in real-world scenarios.

Papers

June 3, 2022

Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress
Rishabh Agarwal, Max Schwarzer, Pablo Samuel Castro, Aaron Courville, Marc G. Bellemare
Reinforcement Learning Deep Reinforcement Learning Much Progress Real World Reinforcement Learning Value Based Reinforcement Learning Tabular Reinforcement Learning

March 23, 2022

Asynchronous Reinforcement Learning for Real-Time Control of Physical Robots
Yufeng Yuan, A. Rupam Mahmood
Reinforcement Learning Real Time Sequential Learning Physical Robot Real World Reinforcement Learning Asynchronous Learning

February 9, 2022

Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration
Desik Rengarajan, Gargi Vaidya, Akshay Sarvesh, Dileep Kalathil, Srinivas Shakkottai
Reinforcement Learning Sparse Reward Efficient Reinforcement Learning Human Guidance Optimal Behavior Real World Reinforcement Learning Reward Feedback

December 27, 2021

Safe Reinforcement Learning with Chance-constrained Model Predictive Control
Samuel Pfrommer, Tanmay Gautam, Alec Zhou, Somayeh Sojoudi
Predictive Control Policy Gradient Safe Reinforcement Learning Real World Reinforcement Learning Optimal Safe Policy

December 18, 2021

Curriculum Based Reinforcement Learning of Grid Topology Controllers to Prevent Thermal Cascading
Amarsagar Reddy Ramapuram Matavalam, Kishan Prudhvi Guddanti, Yang Weng, Venkataramana Ajjarapu
Reinforcement Learning Cascade Model Curriculum Reinforcement Learning Real World Reinforcement Learning Training Agent Power Network

November 25, 2021

Real-world challenges for multi-agent reinforcement learning in grid-interactive buildings
Kingsley Nweye, Bo Liu, Peter Stone, Zoltan Nagy
Reinforcement Learning Multi Agent Reinforcement Learning Real World Real World Reinforcement Learning

January 21, 2020

Unsupervisedly Learned Representations: Should the Quest be Over?
Daniel N. Nissani (Nissensohn)
Reinforcement Learning Representation Learning Supervised Learning Unsupervised Learning Learned Representation Real World Reinforcement Learning QueST

Real World Reinforcement Learning

Papers

Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress

Asynchronous Reinforcement Learning for Real-Time Control of Physical Robots

Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration

Safe Reinforcement Learning with Chance-constrained Model Predictive Control

Curriculum Based Reinforcement Learning of Grid Topology Controllers to Prevent Thermal Cascading

Real-world challenges for multi-agent reinforcement learning in grid-interactive buildings

Unsupervisedly Learned Representations: Should the Quest be Over?