Goal Conditioned

Goal-conditioned (GC) learning focuses on training agents to achieve specific goals, a crucial aspect of artificial intelligence research. Current research emphasizes improving the efficiency and robustness of GC methods, particularly for long-horizon tasks, using techniques like hierarchical reinforcement learning, diffusion models, and transformer-based architectures. These advancements are driven by the need for more sample-efficient and generalizable agents, impacting fields such as robotics, natural language processing, and autonomous systems by enabling more adaptable and capable intelligent systems. The development of effective GC methods is crucial for creating agents that can successfully navigate complex, real-world scenarios.

Papers

November 13, 2024

Offline Adaptation of Quadruped Locomotion using Diffusion Models
Reece O'Mahoney, Alexander L. Mitchell, Wanming Yu, Ingmar Posner, Ioannis Havoutis
Diffusion Model Human Like Locomotion Behavior Diffusion Based Quadrupedal Locomotion Goal Conditioned Quadruped Locomotion Locomotion Strategy

November 3, 2024

Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning
Yuanlin Duan, Guofeng Cui, He Zhu
Reinforcement Learning Goal Conditioned Reinforcement Learning Manipulation Edge Detection Module Goal Conditioned Latent State Model Goal Exploration

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

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 7, 2024

Navigating the Human Maze: Real-Time Robot Pathfinding with Generative Imitation Learning
Martin Moder, Stephen Adhisaputra, Josef Pauli
Robot Trajectory Maze Environment Goal Conditioned Sampling Based Model Predictive Control Generative Adversarial Imitation Proactive Robot

July 18, 2024

Learning Goal-Conditioned Representations for Language Reward Models
Vaskar Nath, Dylan Slack, Jeff Da, Yuntao Ma, Hugh Zhang, Spencer Whitehead, Sean Hendryx
Reinforcement Learning Reward Model Self Supervised Objective Traditional Reinforcement Learning Goal Conditioned Language Reward Reward Model Training

July 8, 2024

Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals
Moritz Reuss, Ömer Erdinç Yağmurlu, Fabian Wenzel, Rudolf Lioutikov
Vision Transformer Goal Conditioned Multimodal Goal

June 20, 2024

One Fling to Goal: Environment-aware Dynamics for Goal-conditioned Fabric Flinging
Linhan Yang, Lei Yang, Haoran Sun, Zeqing Zhang, Haibin He, Fang Wan, Chaoyang Song, Jia Pan
Real World Pseudo Goal Goal Conditioned Environment Dynamic Goal Conditioned Manipulation

May 29, 2024

Multi-objective Cross-task Learning via Goal-conditioned GPT-based Decision Transformers for Surgical Robot Task Automation
Jiawei Fu, Yonghao Long, Kai Chen, Wang Wei, Qi Dou
Decision Transformer Surgical Robot Goal Conditioned Multi Objective Learning Surgical Automation

February 11, 2024

Stitching Sub-Trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL
Sungyoon Kim, Yunseon Choi, Daiki E. Matsunaga, Kee-Eung Kim
Conditional Diffusion Model Long Horizon Planning Goal Conditioned Diverse Skill Offline Handwritten Text Offline Goal Conditioned Reinforcement Learning Trajectory Stitching Offline Goal Conditioned RL

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

September 28, 2023

Efficiency Separation between RL Methods: Model-Free, Model-Based and Goal-Conditioned
Brieuc Pinon, Raphaël Jungers, Jean-Charles Delvenne
Reinforcement Learning Model Free Reinforcement Learning Optimal Behavior Goal Conditioned Inverse Dynamic

September 24, 2023

Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout
Haoran Wang, Zeshen Tang, Leya Yang, Yaoru Sun, Fang Wang, Siyu Zhang, Yeming Chen
Hierarchical Reinforcement Learning Goal Conditioned Model Rollouts Mutual Guidance

July 7, 2023

Goal-Conditioned Predictive Coding for Offline Reinforcement Learning
Zilai Zeng, Ce Zhang, Shijie Wang, Chen Sun
Offline Reinforcement Learning Predictive Coding Goal Conditioned Policy Goal Conditioned

June 30, 2023

Landmark Guided Active Exploration with State-specific Balance Coefficient
Fei Cui, Jiaojiao Fang, Mengke Yang, Guizhong Liu
Value Function Hierarchical Reinforcement Learning Goal Conditioned Unsupervised Exploration State Adaptive

June 19, 2023

LARG, Language-based Automatic Reward and Goal Generation
Julien Perez, Denys Proux, Claude Roux, Michael Niemaz
Robot Learning Multi Task Reinforcement Learning Goal Conditioned Language Guided Robotic Manipulation Goal Generation

April 5, 2023

Goal-Conditioned Imitation Learning using Score-based Diffusion Policies
Moritz Reuss, Maximilian Li, Xiaogang Jia, Rudolf Lioutikov
Goal Conditioned Policy Goal Conditioned Behavior Generation Goal Conditioned Imitation

February 15, 2023

From Prediction to Planning With Goal Conditioned Lane Graph Traversals
Marcel Hallgarten, Martin Stoll, Andreas Zell
Human Prediction Automated Driving Motion Prediction Navigation Task Pseudo Goal Goal Conditioned Lane Graph

February 10, 2023

Language Decision Transformers with Exponential Tilt for Interactive Text Environments
Nicolas Gontier, Pau Rodriguez, Issam Laradji, David Vazquez, Christopher Pal
Transformer Language Model Decision Transformer Tilting Angle Goal Conditioned Language Transformer Text Based Game Environment

January 21, 2023

Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction
Shaofei Cai, Zihao Wang, Xiaojian Ma, Anji Liu, Yitao Liang
Open World Goal Conditioned Policy Goal Conditioned Backbone Fine Tuning Multi Task Agent

Goal Conditioned

Papers

Offline Adaptation of Quadruped Locomotion using Diffusion Models

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

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

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

Navigating the Human Maze: Real-Time Robot Pathfinding with Generative Imitation Learning

Learning Goal-Conditioned Representations for Language Reward Models

Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals

One Fling to Goal: Environment-aware Dynamics for Goal-conditioned Fabric Flinging

Multi-objective Cross-task Learning via Goal-conditioned GPT-based Decision Transformers for Surgical Robot Task Automation

Stitching Sub-Trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL

Goal-conditioned Offline Planning from Curious Exploration

Efficiency Separation between RL Methods: Model-Free, Model-Based and Goal-Conditioned

Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout

Goal-Conditioned Predictive Coding for Offline Reinforcement Learning

Landmark Guided Active Exploration with State-specific Balance Coefficient

LARG, Language-based Automatic Reward and Goal Generation

Goal-Conditioned Imitation Learning using Score-based Diffusion Policies

From Prediction to Planning With Goal Conditioned Lane Graph Traversals

Language Decision Transformers with Exponential Tilt for Interactive Text Environments

Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction