Adaptive Exploration

Adaptive exploration in reinforcement learning focuses on developing efficient strategies for agents to learn effectively in complex environments with limited data or sparse rewards. Current research emphasizes methods that dynamically adjust exploration strategies based on performance, incorporating techniques like variance-based exploration, Bayesian optimization, and program-based strategy induction, often within the framework of algorithms such as Proximal Policy Optimization (PPO). These advancements aim to improve data efficiency and learning stability in various applications, from robotics and combinatorial optimization to material discovery and game playing, by intelligently balancing exploration and exploitation.

Papers

May 13, 2024

Adaptive Exploration for Data-Efficient General Value Function Evaluations
Arushi Jain, Josiah P. Hanna, Doina Precup
Reinforcement Learning Value Function Adaptive Exploration Variance Estimation

May 7, 2024

Proximal Policy Optimization with Adaptive Exploration
Andrei Lixandru
Reinforcement Learning Proximal Policy Optimization Adaptive Exploration

February 26, 2024

Program-Based Strategy Induction for Reinforcement Learning
Carlos G. Correa, Thomas L. Griffiths, Nathaniel D. Daw
Reinforcement Learning Adaptive Exploration Strategy Discovery Program Induction

February 20, 2024

Towards accelerating physical discovery via non-interactive and interactive multi-fidelity Bayesian Optimization: Current challenges and future opportunities
Arpan Biswas, Sai Mani Prudhvi Valleti, Rama Vasudevan, Maxim Ziatdinov, Sergei V. Kalinin
Active Learning Bayesian Optimization Scientific Discovery Multi Fidelity Bayesian Optimization Current Challenge Adaptive Exploration

December 27, 2023

Adaptive trajectory-constrained exploration strategy for deep reinforcement learning
Guojian Wang, Faguo Wu, Xiao Zhang, Ning Guo, Zhiming Zheng
Deep Reinforcement Learning Multi Agent Reinforcement Learning Adaptive Importance Exploration Problem Trajectory Wise Reward Adaptive Exploration Constrained Exploration

June 5, 2023

Meta-SAGE: Scale Meta-Learning Scheduled Adaptation with Guided Exploration for Mitigating Scale Shift on Combinatorial Optimization
Jiwoo Son, Minsu Kim, Hyeonah Kim, Jinkyoo Park
Deep Reinforcement Learning Guided Exploration Dynamic Adaptation Adaptive Exploration

April 26, 2023

FLEX: an Adaptive Exploration Algorithm for Nonlinear Systems
Matthieu Blanke, Marc Lelarge
Model Based Reinforcement Learning Nonlinear Dynamic Nonlinear Model Active Exploration Dynamic Control Adaptive Exploration

April 21, 2023

On the Importance of Exploration for Real Life Learned Algorithms
Steffen Gracla, Carsten Bockelmann, Armin Dekorsy
Practical Algorithm Real World Environment Exploration Importance Aware Deep Q Network Adaptive Exploration Greedy Exploration Entropy Exploration

December 20, 2022

Adapting the Exploration Rate for Value-of-Information-Based Reinforcement Learning
Isaac J. Sledge, Jose C. Principe
Reinforcement Learning Action Selection Adaptive Exploration Exploration Characteristic

July 19, 2022

Abstract Demonstrations and Adaptive Exploration for Efficient and Stable Multi-step Sparse Reward Reinforcement Learning
Xintong Yang, Ze Ji, Jing Wu, Yu-kun Lai
Reinforcement Learning Deep Reinforcement Learning High Efficiency Sparse Reward Video Demonstration DQN Agent Adaptive Exploration

June 16, 2022

Combinatorial Pure Exploration of Causal Bandits
Nuoya Xiong, Wei Chen
Causal Bandit Adaptive Exploration Combinatorial Pure Exploration

June 14, 2022

Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning
Nicolas Castanet, Sylvain Lamprier, Olivier Sigaud
Stein Variational Gradient Descent Variational Objective Exploration Problem Adaptive Exploration Multi Goal Reinforcement Learning

March 29, 2022

When to Go, and When to Explore: The Benefit of Post-Exploration in Intrinsic Motivation
Zhao Yang, Thomas M. Moerland, Mike Preuss, Aske Plaat
Reinforcement Learning Complementary Benefit Intrinsic Motivation POST Exploration Adaptive Exploration

March 25, 2021

Active Inference Tree Search in Large POMDPs
Domenico Maisto, Francesco Gregoretti, Karl Friston, Giovanni Pezzulo
Active Inference Linear MDPs AI Planning Model Based Planning Adaptive Exploration

Adaptive Exploration

Papers

Adaptive Exploration for Data-Efficient General Value Function Evaluations

Proximal Policy Optimization with Adaptive Exploration

Program-Based Strategy Induction for Reinforcement Learning

Towards accelerating physical discovery via non-interactive and interactive multi-fidelity Bayesian Optimization: Current challenges and future opportunities

Adaptive trajectory-constrained exploration strategy for deep reinforcement learning

Meta-SAGE: Scale Meta-Learning Scheduled Adaptation with Guided Exploration for Mitigating Scale Shift on Combinatorial Optimization

FLEX: an Adaptive Exploration Algorithm for Nonlinear Systems

On the Importance of Exploration for Real Life Learned Algorithms

Adapting the Exploration Rate for Value-of-Information-Based Reinforcement Learning

Abstract Demonstrations and Adaptive Exploration for Efficient and Stable Multi-step Sparse Reward Reinforcement Learning

Combinatorial Pure Exploration of Causal Bandits

Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning

When to Go, and When to Explore: The Benefit of Post-Exploration in Intrinsic Motivation

Active Inference Tree Search in Large POMDPs