exploration-exploitation 开源项目推荐（75 个）

opendilab /DI-engine

OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.

wzhe06 /Reco-papers

Classic papers and resources on recommendation

tigerneil /awesome-deep-rl

为了深度RL和人工智能的未来。

imsheridan /DeepRec

推荐、广告工业界经典以及最前沿的论文、资料集合/ Must-read Papers on Recommendation System and CTR Prediction

david-cortes /contextualbandits

Python implementations of contextual bandits algorithms

opendilab /awesome-exploration-rl

A curated list of awesome exploration RL resources (continually updated)

YaoYao1995 /MEEE

Code to reproduce the experiments in Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation (MEEE).

jaimasih05-commits /swarm-foraging-qlearn

Q-Learning Swarm Foraging 2026: Multi-Agent RL in Dynamic Grid Environments

TianhongDai /self-imitation-learning-pytorch

This is the pytorch implementation of ICML 2018 paper - Self-Imitation Learning.

holarissun /RewardShifting

Code for NeurIPS 2022 paper Exploiting Reward Shifting in Value-Based Deep RL

stratisMarkou /sample-efficient-bayesian-rl

Source for the sample efficient tabular RL submission to the 2019 NIPS workshop on Biological and Artificial RL

hmishfaq /LSAC

The official code release for "Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning", ICLR 2025

gokceuludogan /interactive-music-recommendation

Personalized and Interactive Music Recommendation with Bandit approach

hmishfaq /LMC-LSVI

The official code release for Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo, ICLR 2024.

Amshra267 /Thompson-Greedy-Comparison-for-MultiArmed-Bandits

Repository Containing Comparison of two methods for dealing with Exploration-Exploitation dilemma for MultiArmed Bandits

guptav96 /bandit-algorithms

A short implementation of bandit algorithms - ETC, UCB, MOSS and KL-UCB

kkm24132 /ReinforcementLearning

Focuses on Reinforcement Learning related concepts, use cases, and learning approaches

mbhenaff /neural-e3

该项目在 GitHub 上没有填写描述

kakaobrain /leco

Official implementation of LECO (NeurIPS'22)

baturaysaglam /DISCOVER

Deep Intrinsically Motivated Exploration in Continuous Control