Meta RL

Meta-reinforcement learning (Meta-RL) aims to develop agents that can quickly adapt to new tasks with minimal training data, leveraging prior experience to improve learning efficiency. Current research emphasizes improving sample efficiency and generalization capabilities through model-based approaches, incorporating uncertainty quantification, and exploring novel architectures like hypernetworks and decoupled learning frameworks. These advancements hold significant promise for applications requiring rapid adaptation in data-scarce environments, such as robotics and personalized medicine, by enabling more robust and efficient reinforcement learning algorithms.

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

February 25, 2024

DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning
Anthony Liang, Guy Tennenholtz, Chih-wei Hsu, Yinlam Chow, Erdem Bıyık, Craig Boutilier
Meta Reinforcement Learning Dynamic Model Latent State Prior Network Meta RL

December 11, 2023

Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skills
Hongcai He, Anjie Zhu, Shuang Liang, Feiyu Chen, Jie Shao
Prior Knowledge Meta Reinforcement Learning Meta Training Robust Skill Offline Meta Reinforcement Learning Meta RL

November 13, 2023

Data-Efficient Task Generalization via Probabilistic Model-based Meta Reinforcement Learning
Arjun Bhardwaj, Jonas Rothfuss, Bhavya Sukhija, Yarden As, Marco Hutter, Stelian Coros, Andreas Krause
Meta Reinforcement Learning Task Generalization Meta RL

October 12, 2023

MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning
Zeyuan Ma, Hongshu Guo, Jiacheng Chen, Zhenrui Li, Guojun Peng, Yue-Jiao Gong, Yining Ma, Zhiguang Cao
Reinforcement Learning Benchmark Platform Black Box Optimization Metadata Information Meta RL

June 28, 2023

RL$^3$: Boosting Meta Reinforcement Learning via RL inside RL$^2$
Abhinav Bhatia, Samer B. Nashed, Shlomo Zilberstein
Data Efficient Meta Reinforcement Learning Human Like RL Meta RL

November 28, 2022

Hypernetworks for Zero-shot Transfer in Reinforcement Learning
Sahand Rezaei-Shoshtari, Charlotte Morissette, Francois Robert Hogan, Gregory Dudek, David Meger
Reinforcement Learning Zero Shot Transfer Attention Hypernetworks DeepMind Control Suite Optimal Reinforcement Learning Meta RL

October 26, 2022

Uncertainty-based Meta-Reinforcement Learning for Robust Radar Tracking
Julius Ott, Lorenzo Servadei, Gianfranco Mauro, Thomas Stadelmayer, Avik Santra, Robert Wille
Uncertainty Estimation Method Meta RL Robust Radar

October 19, 2022

Oracles & Followers: Stackelberg Equilibria in Deep Multi-Agent Reinforcement Learning
Matthias Gerstgrasser, David C. Parkes
Confidence Oracle Stackelberg Equilibrium Meta RL

June 7, 2022

On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning
Zhao Mandi, Pieter Abbeel, Stephen James
Fine Tuning Multi Task Meta Learning Meta Reinforcement Learning Meta RL

December 14, 2021

How to Learn and Represent Abstractions: An Investigation using Symbolic Alchemy
Badr AlKhamissi, Akshay Srinivasan, Zeb-Kurth Nelson, Sam Ritter
Comprehensive Investigation Metric Aware Abstraction Deep Reinforcement Learning Agent Meta RL Symbolic Concept