A PyTorch Library for Meta-learning Research

Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning

TorchOpt is an efficient library for differentiable optimization built upon PyTorch.

Simple (but often Strong) Baselines for POMDPs in PyTorch, ICML 2022

Re-implementations of SOTA RL algorithms.

"모두를 위한 메타러닝" 책에 대한 코드 저장소

Official Implementation for "In-Context Reinforcement Learning for Variable Action Spaces"

This repo contains the implementation of some new papers on some advanced topics of machine learning e.g. meta-learning, reinforcement-learning, meta-reinforcement-learning, continual-learning and etc.

Code for FOCAL Paper Published at ICLR 2021

Reimplementing existing learning-based ABR algorithms for dynamic video streaming. These algorithms were implemented with Pytorch and python3

Repo to reproduce the First-Explore paper results

Implementation of our paper "Meta Reinforcement Learning with Task Embedding and Shared Policy"

Official Implementation for "In-Context Reinforcement Learning from Noise Distillation"

A curated list of awesome Meta Reinforcement Learning

Implementation of Model-Agnostic Meta-Learning (MAML) applied on Reinforcement Learning problems in TensorFlow 2.

Benchmarking general decision-making with open & random worlds

My notes on reinforcement learning papers

The code and methods offered in Awesome-META+: https://wangjingyao07.github.io/Awesome-Meta-Learning-Platform/

Implementation of BIMRL: Brain Inspired Meta Reinforcement Learning - Roozbeh Razavi et al. (IROS 2022)

Toy meta-RL environments for testing algorithms implementations

Learning to reinforcement learn for Neural Architecture Search

No description provided.

GenReL-World is a general Reinforcement Learning framework to utilize various world models as environments for robot manipulation

An implementation of Meta RL submitted as a course project for the course EE675A (Introduction to Reinforcement Learning)

An repo about the meta reinforcement learning, how an neural network is generalized across range of tasks

Meta Reinforcement Learning tests based on Sinergym environments.

Environment for "Discovering Reinforcement Learning Algorithms"

Minimal RL² implementation using Flax NNX on XLand-MiniGrid.

Constraint‑Aware Meta‑Optimizer for Policy‑Gradient RL

JAX/Flax implementations of ULEE, DIAYN, RND, RL² and PPO. Code for the paper “Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals”