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 13, 2022

Goal-Conditioned Reinforcement Learning in the Presence of an Adversary
Carlos Purves, Pietro Liò, Cătălina Cangea
Reinforcement Learning Robotics Domain Speech Presence Robust Policy Goal Conditioned Reinforcement Learning Adversary Agent Goal Conditioned

November 1, 2022

Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning
Riashat Islam, Hongyu Zang, Anirudh Goyal, Alex Lamb, Kenji Kawaguchi, Xin Li, Romain Laroche, Yoshua Bengio, Remi Tachet Des Combes
Cognitive Abstraction Goal Conditioned Reinforcement Learning Discrete Representation Maze Environment Goal Conditioned Agent

October 28, 2022

Goal Exploration Augmentation via Pre-trained Skills for Sparse-Reward Long-Horizon Goal-Conditioned Reinforcement Learning
Lisheng Wu, Ke Chen
Pre Trained Goal Conditioned Reinforcement Learning Sub Goal Goal Exploration

October 26, 2022

D-Shape: Demonstration-Shaped Reinforcement Learning via Goal Conditioning
Caroline Wang, Garrett Warnell, Peter Stone
Reinforcement Learning Sparse Reward Reward Shaping Goal Conditioned Reinforcement Learning Consistent Conditioning Task Demonstration

September 26, 2022

Overcoming Referential Ambiguity in Language-Guided Goal-Conditioned Reinforcement Learning
Hugo Caselles-Dupré, Olivier Sigaud, Mohamed Chetouani
Natural Language Artificial Agent Goal Conditioned Reinforcement Learning Inductive Reasoning Referential Ambiguity

August 17, 2022

Metric Residual Networks for Sample Efficient Goal-Conditioned Reinforcement Learning
Bo Liu, Yihao Feng, Qiang Liu, Peter Stone
Neural Architecture Neural Network Architecture Goal Conditioned Reinforcement Learning

July 19, 2022

Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning
Wenhao Ding, Haohong Lin, Bo Li, Ding Zhao
Reinforcement Learning Causal Discovery Causal Graph Goal Conditioned Reinforcement Learning Causal Reinforcement Learning Variational Causal

July 4, 2022

Goal-Conditioned Generators of Deep Policies
Francesco Faccio, Vincent Herrmann, Aditya Ramesh, Louis Kirsch, Jürgen Schmidhuber
Goal Conditioned Reinforcement Learning Single Agent Reinforcement Learning Neural Network Policy Deep Policy Expressive Policy Conditioned Generation

June 19, 2022

A Survey on Model-based Reinforcement Learning
Fan-Ming Luo, Tian Xu, Hang Lai, Xiong-Hui Chen, Weinan Zhang, Yang Yu
Reinforcement Learning Timely Survey Multi Agent Reinforcement Learning Model Based Reinforcement Learning Goal Conditioned Reinforcement Learning Model Learning

June 15, 2022

Contrastive Learning as Goal-Conditioned Reinforcement Learning
Benjamin Eysenbach, Tianjun Zhang, Ruslan Salakhutdinov, Sergey Levine
Reinforcement Learning Contrastive Learning Goal Conditioned Reinforcement Learning Contrastive Reinforcement Learning

June 9, 2022

Pragmatically Learning from Pedagogical Demonstrations in Multi-Goal Environments
Hugo Caselles-Dupré, Olivier Sigaud, Mohamed Chetouani
Video Demonstration Goal Conditioned Reinforcement Learning Pragmatic Reasoning Multi Goal Multi Goal Reinforcement Learning Goal Inference Optimal Demonstration

May 20, 2022

A Fully Controllable Agent in the Path Planning using Goal-Conditioned Reinforcement Learning
GyeongTaek Lee
Path Planning Reward Shaping Goal Conditioned Reinforcement Learning Controllable Agent

May 17, 2022

Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space
Kuan Fang, Patrick Yin, Ashvin Nair, Sergey Levine
Latent Space Offline Reinforcement Learning Long Horizon Task Goal Conditioned Reinforcement Learning Pseudo Goal Goal Conditioned Policy Online Fine Tuning Model Free Policy

May 4, 2022

State Representation Learning for Goal-Conditioned Reinforcement Learning
Lorenzo Steccanella, Anders Jonsson
State Representation Goal Conditioned Reinforcement Learning Goal Conditioned Policy Reward Free Reinforcement Learning Multi Goal

April 27, 2022

Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning
Philippe Hansen-Estruch, Amy Zhang, Ashvin Nair, Patrick Yin, Sergey Levine
Reinforcement Learning Goal Conditioned Reinforcement Learning Bisimulation Metric State Reward Creative Analogy Goal Conditioned Agent

February 28, 2022

Weakly Supervised Disentangled Representation for Goal-conditioned Reinforcement Learning
Zhifeng Qian, Mingyu You, Hongjun Zhou, Bin He
Goal Conditioned Reinforcement Learning Visual Reinforcement Learning Goal Conditioned Policy Generalization

February 24, 2022

All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL
Kai Arulkumaran, Dylan R. Ashley, Jürgen Schmidhuber, Rupesh K. Srivastava
Reinforcement Learning Imitation Learning Supervised Learning Goal Conditioned Reinforcement Learning Human Like RL

February 9, 2022

Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL
Rui Yang, Yiming Lu, Wenzhe Li, Hao Sun, Meng Fang, Yali Du, Xiu Li, Lei Han, Chongjie Zhang
Offline Reinforcement Learning New Connection Goal Conditioned Reinforcement Learning

January 20, 2022

Goal-Conditioned Reinforcement Learning: Problems and Solutions
Minghuan Liu, Menghui Zhu, Weinan Zhang
Reinforcement Learning Solution Path Related Problem Goal Conditioned Reinforcement Learning Pseudo Goal

November 18, 2021

Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning
Christopher Hoang, Sungryull Sohn, Jongwook Choi, Wilka Carvalho, Honglak Lee
Efficient Exploration Goal Conditioned Reinforcement Learning Goal Conditioned Policy Successor Feature

Goal Conditioned Reinforcement Learning

Papers

Goal-Conditioned Reinforcement Learning in the Presence of an Adversary

Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning

Goal Exploration Augmentation via Pre-trained Skills for Sparse-Reward Long-Horizon Goal-Conditioned Reinforcement Learning

D-Shape: Demonstration-Shaped Reinforcement Learning via Goal Conditioning

Overcoming Referential Ambiguity in Language-Guided Goal-Conditioned Reinforcement Learning

Metric Residual Networks for Sample Efficient Goal-Conditioned Reinforcement Learning

Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning

Goal-Conditioned Generators of Deep Policies

A Survey on Model-based Reinforcement Learning

Contrastive Learning as Goal-Conditioned Reinforcement Learning

Pragmatically Learning from Pedagogical Demonstrations in Multi-Goal Environments

A Fully Controllable Agent in the Path Planning using Goal-Conditioned Reinforcement Learning

Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space

State Representation Learning for Goal-Conditioned Reinforcement Learning

Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning

Weakly Supervised Disentangled Representation for Goal-conditioned Reinforcement Learning

All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL

Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL

Goal-Conditioned Reinforcement Learning: Problems and Solutions

Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning