Efficient Exploration

Efficient exploration in reinforcement learning and related fields aims to optimize the process of discovering valuable states and actions within complex environments, minimizing wasted effort and maximizing learning efficiency. Current research focuses on developing novel algorithms and model architectures, such as Bayesian actor-critic methods, hierarchical reinforcement learning, and those incorporating intrinsic motivation or large language models, to guide exploration strategically. These advancements are crucial for improving the sample efficiency of reinforcement learning agents, enabling their application to real-world problems with limited data and computational resources, particularly in robotics, search and rescue, and material science. The ultimate goal is to create agents that learn effectively and safely in diverse, challenging environments.

Papers

November 13, 2024

Learning Dynamic Cognitive Map with Autonomous Navigation
Daria de Tinguy, Tim Verbelen, Bart Dhoedt
Autonomous Navigation Efficient Exploration Active Inference Cognitive Map

November 6, 2024

CPEG: Leveraging Consistency Policy with Consensus Guidance for Multi-agent Exploration
Yuqian Fu, Yuanheng Zhu, Haoran Li, Zijie Zhao, Jiajun Chai, Dongbin Zhao
Strong Consistency Efficient Exploration Cooperative Agent Multi Agent MuJoCo Multi Agent Particle Multi Agent Exploration Consensus Formation

October 26, 2024

Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL
Andrew Wagenmaker, Kevin Huang, Liyiming Ke, Byron Boots, Kevin Jamieson, Abhishek Gupta
Reinforcement Learning Simulation Study Efficient Exploration Human Like RL Real World Reinforcement Learning

October 25, 2024

Offline-to-Online Multi-Agent Reinforcement Learning with Offline Value Function Memory and Sequential Exploration
Hai Zhong, Xun Wang, Zhuoran Li, Longbo Huang
Reinforcement Learning Multi Agent Reinforcement Learning Efficient Exploration Multi Agent Challenge Offline Data Binary Forward Exploration Unified Memory

October 23, 2024

Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration
Max Wilcoxson, Qiyang Li, Kevin Frans, Sergey Levine
Reinforcement Learning High Efficiency Environment Exploration Unlabeled Data Efficient Exploration Unsupervised Pre Training Robust Skill Multiple Trajectory

October 12, 2024

ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning
Yarden As, Bhavya Sukhija, Lenart Treven, Carmelo Sferrazza, Stelian Coros, Andreas Krause
Reinforcement Learning LeArning Abstract Efficient Exploration Safety Constraint Positive Reinforcement Active Exploration Safe Exploration

October 10, 2024

Meta-Learning Integration in Hierarchical Reinforcement Learning for Advanced Task Complexity
Arash Khajooeinejad, Masoumeh Chapariniya
Hierarchical Reinforcement Learning Efficient Exploration Task Adaptation Hierarchical Agent Hierarchical Policy

October 4, 2024

Multi-Objective Risk Assessment Framework for Exploration Planning Using Terrain and Traversability Analysis
Riana Gagnon Souleiman, Vivek Shankar Varadharajan, Giovanni Beltrame
Efficient Exploration Efficient Path Planning Traversability Analysis Binary Forward Exploration Unconstrained Environment Exploration Planner

October 2, 2024

Adaptive teachers for amortized samplers
Minsu Kim, Sanghyeok Choi, Taeyoung Yun, Emmanuel Bengio, Leo Feng, Jarrid Rector-Brooks, Sungsoo Ahn, Jinkyoo Park, Nikolay Malkin, Yoshua Bengio
Reinforcement Learning Efficient Exploration Fast Sampling Adaptive Teaching

September 24, 2024

Provably Efficient Exploration in Inverse Constrained Reinforcement Learning
Bo Yue, Jian Li, Guiliang Liu
Efficient Exploration Constrained Optimization Inverse Constrained Reinforcement Learning Constraint Inference

September 20, 2024

Selective Exploration and Information Gathering in Search and Rescue Using Hierarchical Learning Guided by Natural Language Input
Dimitrios Panagopoulos, Adoldo Perrusquia, Weisi Guo
Non Humanoid Robot Autonomous System Hierarchical Reinforcement Learning Efficient Exploration Search and Rescue Hierarchical Learning Natural Language Input Autonomous Capability Information Acquisition

September 17, 2024

September 6, 2024

Goal-Reaching Policy Learning from Non-Expert Observations via Effective Subgoal Guidance
RenMing Huang, Shaochong Liu, Yunqiang Pei, Peng Wang, Guoqing Wang, Yang Yang, Hengtao Shen
Efficient Exploration Policy Actor Critic Subgoal Search Goal Oriented Reinforcement Learning

August 21, 2024

Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction
Anthony GX-Chen, Kenneth Marino, Rob Fergus
Reinforcement Learning World Model Efficient Learning Efficient Exploration Intrinsic Reward Object Level Mapping Aware Policy

August 19, 2024

Efficient Exploration in Deep Reinforcement Learning: A Novel Bayesian Actor-Critic Algorithm
Nikolai Rozanov
Reinforcement Learning Deep Reinforcement Learning Efficient Exploration Modern Reinforcement Learning

July 31, 2024

Image-Based Deep Reinforcement Learning with Intrinsically Motivated Stimuli: On the Execution of Complex Robotic Tasks
David Valencia, Henry Williams, Yuning Xing, Trevor Gee, Minas Liarokapis, Bruce A. MacDonald
Reinforcement Learning Deep Reinforcement Learning Efficient Exploration Intrinsic Motivation Complex Robotic Task Test Stimulus Dense Reward

July 30, 2024

Diffusion Augmented Agents: A Framework for Efficient Exploration and Transfer Learning
Norman Di Palo, Leonard Hasenclever, Jan Humplik, Arunkumar Byravan
Reinforcement Learning Vision Language Model Transfer Learning New Framework Efficient Exploration Hindsight Experience Replay Diffusion Based Augmentation

July 16, 2024

Exciting Action: Investigating Efficient Exploration for Learning Musculoskeletal Humanoid Locomotion
Henri-Jacques Geiß, Firas Al-Hafez, Andre Seyfarth, Jan Peters, Davide Tateo
Action Space Efficient Exploration Action Feature Human Like Locomotion Behavior Bipedal Locomotion Multiple Gait Adversarial Imitation Learning Simulated Humanoid

July 9, 2024

Preference-Guided Reinforcement Learning for Efficient Exploration
Guojian Wang, Faguo Wu, Xiao Zhang, Tianyuan Chen, Xuyang Chen, Lin Zhao
Reinforcement Learning Efficient Exploration Preference Based Reinforcement Learning Trust Region Policy Optimization Trajectory Preference

Efficient Exploration

Papers

Learning Dynamic Cognitive Map with Autonomous Navigation

CPEG: Leveraging Consistency Policy with Consensus Guidance for Multi-agent Exploration

Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL

Offline-to-Online Multi-Agent Reinforcement Learning with Offline Value Function Memory and Sequential Exploration

Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration

ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning

Meta-Learning Integration in Hierarchical Reinforcement Learning for Advanced Task Complexity

Multi-Objective Risk Assessment Framework for Exploration Planning Using Terrain and Traversability Analysis

Adaptive teachers for amortized samplers

Provably Efficient Exploration in Inverse Constrained Reinforcement Learning

Selective Exploration and Information Gathering in Search and Rescue Using Hierarchical Learning Guided by Natural Language Input

Frontier Shepherding: A Bio-Mimetic Multi-robot Framework for Large-Scale Exploration

P2 Explore: Efficient Exploration in Unknown Clustered Environment with Floor Plan Prediction

Goal-Reaching Policy Learning from Non-Expert Observations via Effective Subgoal Guidance

Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction

Efficient Exploration in Deep Reinforcement Learning: A Novel Bayesian Actor-Critic Algorithm

Image-Based Deep Reinforcement Learning with Intrinsically Motivated Stimuli: On the Execution of Complex Robotic Tasks

Diffusion Augmented Agents: A Framework for Efficient Exploration and Transfer Learning

Exciting Action: Investigating Efficient Exploration for Learning Musculoskeletal Humanoid Locomotion

Preference-Guided Reinforcement Learning for Efficient Exploration