Meta Rl Algorithm

Meta-reinforcement learning (Meta-RL) aims to develop agents capable of rapidly adapting to new tasks with minimal training data, leveraging prior experience across multiple related tasks. Current research emphasizes improving sample efficiency and generalization capabilities, focusing on model-based approaches (e.g., using world models and transformers) and addressing issues like gradient bias and distribution shifts in task spaces. These advancements hold significant promise for creating more robust and adaptable AI agents applicable to complex real-world problems, such as robotics and personalized medicine.

Papers

May 22, 2024

Theoretical Analysis of Meta Reinforcement Learning: Generalization Bounds and Convergence Guarantees
Cangqing Wang, Mingxiu Sui, Dan Sun, Zecheng Zhang, Yan Zhou
Generalization Bound Theoretical Analysis Convergence Guarantee Meta Reinforcement Learning Human Like RL Meta Rl Algorithm Meta RL

March 14, 2024

MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning
Zohar Rimon, Tom Jurgenson, Orr Krupnik, Gilad Adler, Aviv Tamar
World Model Mamba in Mamba Meta Reinforcement Learning Reinforcement Learning Benchmark Meta Rl Algorithm Meta RL

December 9, 2023

On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR
Jaeuk Shin, Giho Kim, Howon Lee, Joonho Han, Insoon Yang
High Dimensional Meta Reinforcement Learning Task Inference Meta Rl Algorithm Task Specific Loss Online Linear Quadratic Regulator

November 20, 2022

Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation
Zhizhou Ren, Anji Liu, Yitao Liang, Jian Peng, Jianzhu Ma
Meta Reinforcement Learning Fast Adaptation Reinforcement Learning Benchmark Policy Adaptation Human in the Loop Reinforcement Meta Rl Algorithm

October 6, 2022

Distributionally Adaptive Meta Reinforcement Learning
Anurag Ajay, Abhishek Gupta, Dibya Ghosh, Sergey Levine, Pulkit Agrawal
Meta Reinforcement Learning Distributional Robustness Policy Alignment Meta Reinforcement Meta Rl Algorithm

September 21, 2022

September 11, 2022

Meta-Reinforcement Learning via Language Instructions
Zhenshan Bing, Alexander Koch, Xiangtong Yao, Kai Huang, Alois Knoll
Reinforcement Learning Deep Reinforcement Learning Natural Language Instruction Meta Reinforcement Learning Meta Rl Algorithm Language Instruction Manipulation Benchmark

August 24, 2022

A model-based approach to meta-Reinforcement Learning: Transformers and tree search
Brieuc Pinon, Jean-Charles Delvenne, Raphaël Jungers
Transformer Megatron Decepticons Meta Learning Model Based Model Free Meta Reinforcement Learning Tree Search Meta Rl Algorithm

June 21, 2022

Meta Reinforcement Learning with Finite Training Tasks -- a Density Estimation Approach
Zohar Rimon, Aviv Tamar, Gilad Adler
Density Estimation Meta Reinforcement Learning Task Distribution Meta Rl Algorithm Bayes Optimal Policy

March 31, 2022

Robust Meta-Reinforcement Learning with Curriculum-Based Task Sampling
Morio Matsumoto, Hiroya Matsuba, Toshihiro Kujirai
Meta Reinforcement Learning Meta Rl Algorithm Task Sampling Robust Meta Reinforcement Learning

December 31, 2021

A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning
Xidong Feng, Bo Liu, Jie Ren, Luo Mai, Rui Zhu, Haifeng Zhang, Jun Wang, Yaodong Yang
Reinforcement Learning Meta Learning Theoretical Understanding Meta Reinforcement Learning Meta Gradient Biased Gradient Meta Rl Algorithm

December 1, 2021

On the Practical Consistency of Meta-Reinforcement Learning Algorithms
Zheng Xiong, Luisa Zintgraf, Jacob Beck, Risto Vuorio, Shimon Whiteson
Strong Consistency Meta Reinforcement Learning Consistency Model Meta Rl Algorithm Logical Consistency