TorchOpt is an efficient library for differentiable optimization built upon PyTorch.
-
Updated
May 24, 2024 - Python
TorchOpt is an efficient library for differentiable optimization built upon PyTorch.
JAX-accelerated Meta-Reinforcement Learning Environments Inspired by XLand and MiniGrid 🏎️
Implementation of 'RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning'
Code for paper "Model-based Adversarial Meta-Reinforcement Learning" (https://arxiv.org/abs/2006.08875)
PyTorch implementation of Episodic Meta Reinforcement Learning on variants of the "Two-Step" task. Reproduces the results found in three papers. Check the ReadMe for more details!
A collection of Meta-Reinforcement Learning algorithms in PyTorch
Implementation of Improving Generalization for Neural Adaptive Video Streaming via Meta Reinforcement Learning - N. Kan et al. (ACM MM22)
PyTorch implementation of two variants of the Harlow visual fixation task (PsychLab and 1D version). Reproduces the results found in two papers. Check the ReadMe for more details!
Code for the paper "Meta-Reinforcement Learning by Tracking Task Non-stationarity" (IJCAI 2021)
Python code to implement hard sampling based task representation learning for robust offline meta RL
meta-RL soft actor-critic with BRUNO for task inference
Rapid Policy Transfer in Reinforcement Learning - Graduation Project
Implementation of the paper "MERINA+: Improving Generalization for Neural Video Adaptation via Information-Theoretic Meta-Reinforcement Learning" - N. Kan, et. al., 2023
Add a description, image, and links to the meta-reinforcement-learning topic page so that developers can more easily learn about it.
To associate your repository with the meta-reinforcement-learning topic, visit your repo's landing page and select "manage topics."