Goal Conditioned Reinforcement Learning

Goal-conditioned reinforcement learning (GCRL) focuses on training agents to achieve diverse goals specified as target states or conditions, addressing the challenge of sparse rewards in traditional reinforcement learning. Current research emphasizes improving exploration efficiency in complex environments, often leveraging hierarchical architectures, skill-based approaches, and model-based methods like decision transformers and contrastive learning algorithms. This field is significant for advancing artificial intelligence, particularly in robotics and other domains requiring adaptable, goal-directed behavior, with applications ranging from clinical decision support to autonomous navigation.

Papers

November 3, 2024

October 31, 2024

Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning
Beyazit Yalcinkaya, Niklas Lauffer, Marcell Vazquez-Chanlatte, Sanjit A. Seshia
LeArning Abstract Goal Conditioned Reinforcement Learning Goal Representation Temporal Goal Deterministic Finite Automaton

October 26, 2024

OGBench: Benchmarking Offline Goal-Conditioned RL
Seohong Park, Kevin Frans, Benjamin Eysenbach, Sergey Levine
Reinforcement Learning Goal Conditioned Reinforcement Learning Action Free Offline Offline Goal Conditioned Reinforcement Learning

October 9, 2024

Q-WSL: Optimizing Goal-Conditioned RL with Weighted Supervised Learning via Dynamic Programming
Xing Lei, Xuetao Zhang, Zifeng Zhuang, Donglin Wang
Q Learning Dynamic Programming Goal Conditioned Reinforcement Learning Goal Conditioned

October 4, 2024

Predictive Coding for Decision Transformer
Tung M. Luu, Donghoon Lee, Chang D. Yoo
Offline Reinforcement Learning Policy Learning Sparse Reward Decision Transformer Predictive Coding Goal Conditioned Reinforcement Learning

August 21, 2024

Offline Policy Learning via Skill-step Abstraction for Long-horizon Goal-Conditioned Tasks
Donghoon Kim, Minjong Yoo, Honguk Woo
Policy Learning Goal Conditioned Reinforcement Learning Goal Conditioned Offline Policy Learning Skill Abstraction

August 20, 2024

Accelerating Goal-Conditioned RL Algorithms and Research
Michał Bortkiewicz, Władek Pałucki, Vivek Myers, Tadeusz Dziarmaga, Tomasz Arczewski, Łukasz Kuciński, Benjamin Eysenbach
Reinforcement Learning Reinforcement Learning Algorithm DH Research Self Supervision Goal Conditioned Reinforcement Learning Contrastive Reinforcement Learning

August 4, 2024

Scalable Signal Temporal Logic Guided Reinforcement Learning via Value Function Space Optimization
Yiting He, Peiran Liu, Yiding Ji
Reinforcement Learning Model Based Reinforcement Learning Signal Temporal Logic Goal Conditioned Reinforcement Learning Space Optimality

July 28, 2024

Empowering Clinicians with Medical Decision Transformers: A Framework for Sepsis Treatment
Aamer Abdul Rahman, Pranav Agarwal, Rita Noumeir, Philippe Jouvet, Vincent Michalski, Samira Ebrahimi Kahou
New Framework Decision Transformer Goal Conditioned Reinforcement Learning Clinical Decision Support Sepsis Treatment Clinical Transformer

July 12, 2024

Instruction Following with Goal-Conditioned Reinforcement Learning in Virtual Environments
Zoya Volovikova, Alexey Skrynnik, Petr Kuderov, Aleksandr I. Panov
Human Instruction Goal Conditioned Reinforcement Learning Artificial Intelligence Agent Virtual Environment Language Instruction Pre Trained Reinforcement Learning

July 11, 2024

TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations
Junik Bae, Kwanyoung Park, Youngwoon Lee
Goal Conditioned Reinforcement Learning Goal Conditioned Policy Aware Representation

June 1, 2024

Exploring the limits of Hierarchical World Models in Reinforcement Learning
Robin Schiewer, Anand Subramoney, Laurenz Wiskott
Reinforcement Learning Continuum Limit World Model Hierarchical Reinforcement Learning Goal Conditioned Reinforcement Learning

May 2, 2024

Goal-conditioned reinforcement learning for ultrasound navigation guidance
Abdoul Aziz Amadou, Vivek Singh, Florin C. Ghesu, Young-Ho Kim, Laura Stanciulescu, Harshitha P. Sai, Puneet Sharma, Alistair Young, Ronak Rajani, Kawal Rhode
Contrastive Learning Goal Conditioned Reinforcement Learning Transesophageal Echocardiography Patient Level

April 19, 2024

Goal Exploration via Adaptive Skill Distribution for Goal-Conditioned Reinforcement Learning
Lisheng Wu, Ke Chen
Goal Conditioned Reinforcement Learning Exploration Efficiency Goal Directed Behavior Adaptive Skill Goal Exploration

February 23, 2024

Foundation Policies with Hilbert Representations
Seohong Park, Tobias Kreiman, Sergey Levine
Reinforcement Learning Flawed Foundation Goal Conditioned Reinforcement Learning Self Supervised Objective Unsupervised Version Self Supervised Reinforcement Learning 2 Dimensional Hilbert

February 16, 2024

Learning Goal-Conditioned Policies from Sub-Optimal Offline Data via Metric Learning
Alfredo Reichlin, Miguel Vasco, Hang Yin, Danica Kragic
Optimal Policy Metric Learning Goal Conditioned Reinforcement Learning Goal Conditioned Policy Offline Data Offline Goal Conditioned Reinforcement Learning Offline Goal Conditioned RL

February 14, 2024

Single-Reset Divide & Conquer Imitation Learning
Alexandre Chenu, Olivier Serris, Olivier Sigaud, Nicolas Perrin-Gilbert
Deep Reinforcement Learning Imitation Learning Video Demonstration Goal Conditioned Reinforcement Learning

January 25, 2024

Scilab-RL: A software framework for efficient reinforcement learning and cognitive modeling research
Jan Dohmen, Frank Röder, Manfred Eppe
Reinforcement Learning Efficient Reinforcement Learning Goal Conditioned Reinforcement Learning Robotic Agent Cognitive Model Cognitive Modeling Software Framework

December 12, 2023

ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning
Xiangyu Yin, Sihao Wu, Jiaxu Liu, Meng Fang, Xingyu Zhao, Xiaowei Huang, Wenjie Ruan
Contrastive Learning Adversarial Attack Adversarial Robustness Robust Representation Goal Conditioned Reinforcement Learning

Goal Conditioned Reinforcement Learning

Papers

Diversity Progress for Goal Selection in Discriminability-Motivated RL

Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning

Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning

OGBench: Benchmarking Offline Goal-Conditioned RL

Q-WSL: Optimizing Goal-Conditioned RL with Weighted Supervised Learning via Dynamic Programming

Predictive Coding for Decision Transformer

Offline Policy Learning via Skill-step Abstraction for Long-horizon Goal-Conditioned Tasks

Accelerating Goal-Conditioned RL Algorithms and Research

Scalable Signal Temporal Logic Guided Reinforcement Learning via Value Function Space Optimization

Empowering Clinicians with Medical Decision Transformers: A Framework for Sepsis Treatment

Instruction Following with Goal-Conditioned Reinforcement Learning in Virtual Environments

TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations

Exploring the limits of Hierarchical World Models in Reinforcement Learning

Goal-conditioned reinforcement learning for ultrasound navigation guidance

Goal Exploration via Adaptive Skill Distribution for Goal-Conditioned Reinforcement Learning

Foundation Policies with Hilbert Representations

Learning Goal-Conditioned Policies from Sub-Optimal Offline Data via Metric Learning

Single-Reset Divide & Conquer Imitation Learning

Scilab-RL: A software framework for efficient reinforcement learning and cognitive modeling research

ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning