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

December 7, 2023

Is Feedback All You Need? Leveraging Natural Language Feedback in Goal-Conditioned Reinforcement Learning
Sabrina McCallum, Max Taylor-Davies, Stefano V. Albrecht, Alessandro Suglia
Reinforcement Learning Human Feedback Generalization Performance Goal Conditioned Reinforcement Learning Language Feedback Behaviour Learning

November 29, 2023

Bias Resilient Multi-Step Off-Policy Goal-Conditioned Reinforcement Learning
Lisheng Wu, Ke Chen
Efficient Learning Goal Conditioned Reinforcement Learning Policy Improvement

November 28, 2023

Goal-conditioned Offline Planning from Curious Exploration
Marco Bagatella, Georg Martius
Deep Reinforcement Learning Zero Shot Value Function Goal Conditioned Reinforcement Learning Goal Conditioned Offline Planning Intelligent Exploration

November 1, 2023

A Definition of Open-Ended Learning Problems for Goal-Conditioned Agents
Olivier Sigaud, Gianluca Baldassarre, Cedric Colas, Stephane Doncieux, Richard Duro, Pierre-Yves Oudeyer, Nicolas Perrin-Gilbert, Vieri Giuliano Santucci
Continual LEArning Open Ended Definition Defining Redefinition Goal Conditioned Reinforcement Learning Autotelic Agent Goal Conditioned Agent

October 31, 2023

Contrastive Difference Predictive Coding
Chongyi Zheng, Ruslan Salakhutdinov, Benjamin Eysenbach
Reinforcement Learning Human Prediction Goal Conditioned Reinforcement Learning Contrastive Predictive Coding

October 30, 2023

Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills
Seongun Kim, Kyowoon Lee, Jaesik Choi
Goal Conditioned Reinforcement Learning Unsupervised Discovery Curriculum Reinforcement Learning Robust Skill Variational Empowerment

October 10, 2023

$f$-Policy Gradients: A General Framework for Goal Conditioned RL using $f$-Divergences
Siddhant Agarwal, Ishan Durugkar, Peter Stone, Amy Zhang
Sparse Reward General Framework Goal Conditioned Reinforcement Learning Pseudo Goal F$ Divergence

October 4, 2023

July 22, 2023

HIQL: Offline Goal-Conditioned RL with Latent States as Actions
Seohong Park, Dibya Ghosh, Benjamin Eysenbach, Sergey Levine
Reinforcement Learning Value Function Latent State Past Action Goal Conditioned Reinforcement Learning Unsupervised Pre Training Offline Goal Conditioned Reinforcement Learning Standardized Benchmark Inverse Q Learning

July 20, 2023

Goal-Conditioned Reinforcement Learning with Disentanglement-based Reachability Planning
Zhifeng Qian, Mingyu You, Hongjun Zhou, Xuanhui Xu, Bin He
Goal Conditioned Reinforcement Learning Dimensional State Space State Space Representation

July 16, 2023

Magnetic Field-Based Reward Shaping for Goal-Conditioned Reinforcement Learning
Hongyu Ding, Yuanze Tang, Qing Wu, Bo Wang, Chunlin Chen, Zhi Wang
Reward Shaping Goal Conditioned Reinforcement Learning Permanent Magnet

June 28, 2023

MRHER: Model-based Relay Hindsight Experience Replay for Sequential Object Manipulation Tasks with Sparse Rewards
Yuming Huang, Bin Ren, Ziming Xu, Lianghong Wu
Sparse Reward Goal Conditioned Reinforcement Learning Sequential Manipulation Hindsight Experience Replay

June 24, 2023

Learning from Pixels with Expert Observations
Minh-Huy Hoang, Long Dinh, Hai Nguyen
Reinforcement Learning LeArning Abstract Sparse Reward Tetromino Pixel Goal Conditioned Reinforcement Learning Expert Level Performance Visual Goal Expert Observation

May 17, 2023

Goal-Conditioned Supervised Learning with Sub-Goal Prediction
Tom Jurgenson, Aviv Tamar
Goal Conditioned Reinforcement Learning Goal Conditioned Policy Sub Goal

March 26, 2023

Learning Generative Models with Goal-conditioned Reinforcement Learning
Mariana Vargas Vieyra, Pierre Ménard
Generative Model Scientific Inference Image Synthesis Variational Auto Goal Conditioned Reinforcement Learning Learning Generative Model

March 23, 2023

Planning Goals for Exploration
Edward S. Hu, Richard Chang, Oleh Rybkin, Dinesh Jayaraman
Environment Exploration Goal Conditioned Reinforcement Learning Goal Conditioned Policy Goal Directed Goal Discovery

March 20, 2023

Imitating Graph-Based Planning with Goal-Conditioned Policies
Junsu Kim, Younggyo Seo, Sungsoo Ahn, Kyunghwan Son, Jinwoo Shin
Goal Conditioned Reinforcement Learning Goal Conditioned Policy Graph Based Planning

March 9, 2023

GOATS: Goal Sampling Adaptation for Scooping with Curriculum Reinforcement Learning
Yaru Niu, Shiyu Jin, Zeqing Zhang, Jiacheng Zhu, Ding Zhao, Liangjun Zhang
Goal Conditioned Reinforcement Learning State Action Space Real World Scenario Curriculum Reinforcement Learning

February 7, 2023

Provably Efficient Offline Goal-Conditioned Reinforcement Learning with General Function Approximation and Single-Policy Concentrability
Hanlin Zhu, Amy Zhang
Policy Learning Goal Conditioned Reinforcement Learning Offline Goal Conditioned Reinforcement Learning Single Policy Concentrability