Sparse Reward Environment

Sparse reward environments, characterized by infrequent or delayed feedback signals, pose a significant challenge for reinforcement learning (RL) agents. Current research focuses on improving exploration strategies through intrinsic rewards (e.g., novelty-based methods, information-theoretic approaches), hierarchical RL architectures to decompose complex tasks, and leveraging auxiliary models like vision-language models to provide richer reward signals. These advancements aim to enhance sample efficiency and enable RL agents to solve complex, real-world problems where dense reward functions are impractical or impossible to design, impacting fields like robotics and human-computer interaction.

Papers

December 30, 2023

Policy Optimization with Smooth Guidance Learned from State-Only Demonstrations
Guojian Wang, Faguo Wu, Xiao Zhang, Tianyuan Chen, Zhiming Zheng
Reward Function Policy OpTimization Sparse Reward Environment

December 10, 2023

Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularization
Takuya Hiraoka
Reinforcement Learning Sparse Reward Environment Double Q Learning Dense Reward

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

November 1, 2023

Enhanced Generalization through Prioritization and Diversity in Self-Imitation Reinforcement Learning over Procedural Environments with Sparse Rewards
Alain Andres, Daochen Zha, Javier Del Ser
Reinforcement Learning Sparse Reward Procedural Content Generation Sparse Reward Environment Priority Based Enhancing Generalization Self Instruct

October 10, 2023

Information Content Exploration
Jacob Chmura, Hasham Burhani, Xiao Qi Shi
Efficient Exploration Intrinsic Reward Sparse Reward Environment Knowledge Exploration

August 9, 2023

Beyond Surprise: Improving Exploration Through Surprise Novelty
Hung Le, Kien Do, Dung Nguyen, Svetha Venkatesh
Environment Exploration Intrinsic Reward Sparse Reward Environment Surprise Bound Visual Memory

July 20, 2023

Reparameterized Policy Learning for Multimodal Trajectory Optimization
Zhiao Huang, Litian Liang, Zhan Ling, Xuanlin Li, Chuang Gan, Hao Su
Reinforcement Learning Policy Gradient Action Space Sparse Reward Environment Multimodal Reinforcement Learning Multimodal Optimization

July 11, 2023

Boosting Feedback Efficiency of Interactive Reinforcement Learning by Adaptive Learning from Scores
Shukai Liu, Chenming Wu, Ying Li, Liangjun Zhang
Adaptive Learning Performance Score Sparse Reward Environment Pairwise Preference Interactive Reinforcement Learning User Feedback

June 14, 2023

Skill-Critic: Refining Learned Skills for Reinforcement Learning
Ce Hao, Catherine Weaver, Chen Tang, Kenta Kawamoto, Masayoshi Tomizuka, Wei Zhan
Reinforcement Learning Hierarchical Reinforcement Learning Sparse Reward Environment Robust Skill Refining Method Policy Fine Tuning Skill Mention

May 25, 2023

Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory
Xizhou Zhu, Yuntao Chen, Hao Tian, Chenxin Tao, Weijie Su, Chenyu Yang, Gao Huang, Bin Li, Lewei Lu, Xiaogang Wang, Yu Qiao, Zhaoxiang Zhang, Jifeng Dai
Reinforcement Learning Open World Sparse Reward Environment Agent Failure

March 24, 2023

Safe and Sample-efficient Reinforcement Learning for Clustered Dynamic Environments
Hongyi Chen, Changliu Liu
Reinforcement Learning Algorithm Sparse Reward Environment Sample Efficient Reinforcement Learning

February 28, 2023

Learning Sparse Control Tasks from Pixels by Latent Nearest-Neighbor-Guided Explorations
Ruihan Zhao, Ufuk Topcu, Sandeep Chinchali, Mariano Phielipp
Deep Reinforcement Learning Environment Exploration Sparse Reward Tetromino Pixel Model Free Reinforcement Learning Sparse Reward Environment Intermediate Latent Sparse Semantic Vision Based Reinforcement Learning

February 22, 2023

Self-supervised network distillation: an effective approach to exploration in sparse reward environments
Matej Pecháč, Michal Chovanec, Igor Farkaš
Reinforcement Learning Self Supervised Environment Exploration Reward Function Sparse Reward Environment Intrinsic Motivation Effective Approach

January 21, 2023

The configurable tree graph (CT-graph): measurable problems in partially observable and distal reward environments for lifelong reinforcement learning
Andrea Soltoggio, Eseoghene Ben-Iwhiwhu, Christos Peridis, Pawel Ladosz, Jeffery Dick, Praveen K. Pilly, Soheil Kolouri
Reward Function Sparse Reward Sparse Reward Environment Lifelong Reinforcement Learning Memory Less Agent Solved Problem Hierarchical Reward

December 7, 2022

Curiosity creates Diversity in Policy Search
Paul-Antoine Le Tolguenec, Emmanuel Rachelson, Yann Besse, Dennis G. Wilson
Diversity Awareness Evolution Strategy Sparse Reward Environment Intrinsic Motivation Curiosity Inducing Situation Policy Search Evolutionary Policy Search Reward Transition

November 22, 2022

Efficient Exploration using Model-Based Quality-Diversity with Gradients
Bryan Lim, Manon Flageat, Antoine Cully
Reinforcement Learning Efficient Exploration Quality Diversity Evolution Strategy Sparse Reward Environment

October 23, 2022

Active Exploration for Robotic Manipulation
Tim Schneider, Boris Belousov, Georgia Chalvatzaki, Diego Romeres, Devesh K. Jha, Jan Peters
Robotic Manipulation Model Based Reinforcement Learning Active Exploration Sparse Reward Environment

October 14, 2022

Multi-trainer Interactive Reinforcement Learning System
Zhaori Guo, Timothy J. Norman, Enrico H. Gerding
Sparse Reward Environment Interactive Reinforcement Learning

October 7, 2022

Generative Augmented Flow Networks
Ling Pan, Dinghuai Zhang, Aaron Courville, Longbo Huang, Yoshua Bengio
Sparse Reward Generative Flow Network Sparse Reward Environment

October 4, 2022

Handling Sparse Rewards in Reinforcement Learning Using Model Predictive Control
Murad Dawood, Nils Dengler, Jorge de Heuvel, Maren Bennewitz
Sparse Reward Reward Shaping Sparse Reward Environment

Sparse Reward Environment

Papers

Policy Optimization with Smooth Guidance Learned from State-Only Demonstrations

Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularization

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

Enhanced Generalization through Prioritization and Diversity in Self-Imitation Reinforcement Learning over Procedural Environments with Sparse Rewards

Information Content Exploration

Beyond Surprise: Improving Exploration Through Surprise Novelty

Reparameterized Policy Learning for Multimodal Trajectory Optimization

Boosting Feedback Efficiency of Interactive Reinforcement Learning by Adaptive Learning from Scores

Skill-Critic: Refining Learned Skills for Reinforcement Learning

Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory

Safe and Sample-efficient Reinforcement Learning for Clustered Dynamic Environments

Learning Sparse Control Tasks from Pixels by Latent Nearest-Neighbor-Guided Explorations

Self-supervised network distillation: an effective approach to exploration in sparse reward environments

The configurable tree graph (CT-graph): measurable problems in partially observable and distal reward environments for lifelong reinforcement learning

Curiosity creates Diversity in Policy Search

Efficient Exploration using Model-Based Quality-Diversity with Gradients

Active Exploration for Robotic Manipulation

Multi-trainer Interactive Reinforcement Learning System

Generative Augmented Flow Networks

Handling Sparse Rewards in Reinforcement Learning Using Model Predictive Control