Meta Reinforcement Learning

79 papers with code • 2 benchmarks • 1 datasets

This task has no description! Would you like to contribute one?


Use these libraries to find Meta Reinforcement Learning models and implementations

Most implemented papers

Learning to reinforcement learn

awjuliani/Meta-RL 17 Nov 2016

We unpack these points in a series of seven proof-of-concept experiments, each of which examines a key aspect of deep meta-RL.

Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning

rlworkgroup/metaworld 24 Oct 2019

Therefore, if the aim of these methods is to enable faster acquisition of entirely new behaviors, we must evaluate them on task distributions that are sufficiently broad to enable generalization to new behaviors.

Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables

katerakelly/oyster ICLR Workshop LLD 2019

In our approach, we perform online probabilistic filtering of latent task variables to infer how to solve a new task from small amounts of experience.

PixelSNAIL: An Improved Autoregressive Generative Model

neocxi/pixelsnail-public ICML 2018

Autoregressive generative models consistently achieve the best results in density estimation tasks involving high dimensional data, such as images or audio.

ProMP: Proximal Meta-Policy Search

jonasrothfuss/promp ICLR 2019

Credit assignment in Meta-reinforcement learning (Meta-RL) is still poorly understood.

Diversity is All You Need: Learning Skills without a Reward Function

navneet-nmk/Hierarchical-Meta-Reinforcement-Learning ICLR 2019

On a variety of simulated robotic tasks, we show that this simple objective results in the unsupervised emergence of diverse skills, such as walking and jumping.

Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning

iclavera/learning_to_adapt ICLR 2019

Although reinforcement learning methods can achieve impressive results in simulation, the real world presents two major challenges: generating samples is exceedingly expensive, and unexpected perturbations or unseen situations cause proficient but specialized policies to fail at test time.

Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning

allenai/savn CVPR 2019

In this paper we study the problem of learning to learn at both training and test time in the context of visual navigation.