Our codebase trials provide an implementation of the Select and Trade paper, which proposes a new paradigm for pair trading using hierarchical reinforcement learning. It includes the code for the proposed method and experimental results on real-world stock data to demonstrate its effectiveness.

[NeurIPS2021] Federated Reinforcement Learning with Theoretical Guarantees. The repo contains code and experiments for our Federated Policy Gradient with Byzantine Resilience framework for improving sample efficiency of RL agents.

Publication catalog for research on Federated RL (FRL).

[NeurIPS 2024] Code for Federated Ensemble-Directed Offline Reinforcement Learning

Experiments code for AAMAS'24 paper on "Decentralized Federated Policy Gradient with Byzantine Fault-Tolerance and Provably Fast Convergence"

[AAMAS 2025] Privacy-preserving and Personalized RLHF, with convergence guarantees. The Code contains experiments for training multiple instances of GPT-2 for personalized sentiment aligned text generation.

This repo implements our paper, "Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee", which has been accepted at NuerIPS 2021.

Adaptive Confidence-Weighted Policy Aggregation: A Novel Method for Federated Reinforcement Learning