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

JAX-accelerated Meta-Reinforcement Learning Environments Inspired by XLand and MiniGrid 🏎️

XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning - - —

Implementation of 'RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning'

A collection of Meta-Reinforcement Learning algorithms in PyTorch

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!

Code for paper "Model-based Adversarial Meta-Reinforcement Learning" (https://arxiv.org/abs/2006.08875)

Implementation of Improving Generalization for Neural Adaptive Video Streaming via Meta Reinforcement Learning - N. Kan et al. (ACM MM22)

Next-gen Foundation Model for Embodied AI

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!

Xenoverse is a collection of randomized RL, Language, and general-purpose simulation environments, designed for training General-Purpose Learning Agents (GLAs).

a novel algo for meta-MARL; 元-多智能体强化学习算法

Context-Based Meta-Reinforcement Learning with Bayesian Nonparametric Models (MELTS)

Implementation of the paper "MERINA+: Improving Generalization for Neural Video Adaptation via Information-Theoretic Meta-Reinforcement Learning" - N. Kan, et. al., 2023

Code for the paper "Meta-Reinforcement Learning by Tracking Task Non-stationarity" (IJCAI 2021)

meta-RL soft actor-critic with BRUNO for task inference

Python code to implement hard sampling based task representation learning for robust offline meta RL

Customized environment utilizing the OpenAI Gym library for controlling battery energy storage systems in multi-microgrids

Source code for reproducing free random projection

Rapid Policy Transfer in Reinforcement Learning - Graduation Project