git-disl/PokeLLMon

Stars
167
Rank 226,635 (Top 5 %)
Language
Python
Created 10 months ago
Updated 5 months ago

git-disl/PokeLLMon

git-disl

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

PokéLLMon

This is the implementation for the paper "PokéLLMon: A Human-Parity Agent for Pokémon battles with Large Language Models."

The documentation will be fully updated within 3 days.

Requirements:

python >= 3.8
openai >= 1.7.2

Configuration

Configuring a Local Pokémon Showdown Server (Battle Engine)

Install Node.js v10+.
Clone the Pokémon Showdown repository and set it up:

git clone https://github.com/smogon/pokemon-showdown.git
cd pokemon-showdown
npm install
cp config/config-example.js config/config.js
node pokemon-showdown start --no-security
Enter "http://localhost:8000/" in your browsers.

Configuring OpenAI API

Get GPT-4 API from https://platform.openai.com/account/api-keys

Configuring Players

Register in your account on https://play.pokemonshowdown.com/ and get your password.

from poke_env import AccountConfiguration
# No authentication required for the local server
my_account_config = AccountConfiguration("your_username", "your_password")
player = Player(account_configuration=my_account_config)

# Authentication required for the official showdown server
from poke_env import AccountConfiguration, ShowdownServerConfiguration
my_account_config = AccountConfiguration("your_username", "your_password")
player = Player(account_configuration=my_account_config, server_configuration=ShowdownServerConfiguration)

Let's Play Pokémon Battles!!

Battle Against the Heuristic Bot Locally

python vs_bot.py # fill in your username and password for PokeLLMon

Battle Against a Human Player Locally

First, log into your other account manually on the local server, choosing "[Gen 8] Random Battle".

python vs_local_player.py # fill in your username and password for PokeLLMon

Battle Against Ladder Players on Pokémon Showdown

Open and log in: https://play.pokemonshowdown.com/

python vs_ladder_player.py # fill in your username and password for PokeLLMon, no need to set up local server.

Acknowledgement

The environment is implemented based on Poke Env.

awesome-LLM-game-agent-papers

A Survey on Large Language Model-Based Game Agents

DataPoisoning_FL

Code for Data Poisoning Attacks Against Federated Learning Systems

TOG

Real-time object detection is one of the key applications of deep neural networks (DNNs) for real-world mission-critical systems. While DNN-powered object detection systems celebrate many life-enriching opportunities, they also open doors for misuse and abuse. This project presents a suite of adversarial objectness gradient attacks, coined as TOG, which can cause the state-of-the-art deep object detection networks to suffer from untargeted random attacks or even targeted attacks with three types of specificity: (1) object-vanishing, (2) object-fabrication, and (3) object-mislabeling. Apart from tailoring an adversarial perturbation for each input image, we further demonstrate TOG as a universal attack, which trains a single adversarial perturbation that can be generalized to effectively craft an unseen input with a negligible attack time cost. Also, we apply TOG as an adversarial patch attack, a form of physical attacks, showing its ability to optimize a visually confined patch filled with malicious patterns, deceiving well-trained object detectors to misbehave purposefully.

Jupyter Notebook

BERT4ETH

BERT4ETH: A Pre-trained Transformer for Ethereum Fraud Detection (WWW23)

GPTLens

Large Language Model-Powered Smart Contract Vulnerability Detection: New Perspectives (TPS23)

EllipticPlusPlus

Elliptic++ Dataset: A Graph Network of Bitcoin Blockchain Transactions and Wallet Addresses

Jupyter Notebook

CPL_attack

Jupyter Notebook

awesome_LLM-harmful-fine-tuning-papers

A survey on harmful fine-tuning issue for large language model

scale-fl

Code for ScaleFL

AdaTrace

Utility-aware synthesis of differentially private and attack-resilient location traces

LRBench

A learning rate recommending and benchmarking tool.

CLDP

Secure and utility-aware data collection with condensed local differential privacy

FastSwap

Dynamic and Transparent Memory Sharing for Accelerating Big Data Analytics Workloads in Virtualized Cloud

Vaccine

This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)

EnsembleBench

A holistic framework for promoting high diversity ensemble learning.

XMemPod

A disaggregated memory orchestration system that virtualizes cluster wide memory to scale data intensive, large memory workloads in virtualized clouds

Fed-CDP

Gradient-Leakage Resilient Federated Learning

DLEdge

This project accelerates deep learning models on the edge with the support of running ensemble learning for performance improvement. The current version accelerates YOLO object detectors with Intel Neural Compute Stick 2 using parallel programming.

Lockdown

A backdoor defense for federated learning via isolated subspace training (NeurIPS2023)

EENet

Code for Adaptive Deep Neural Network Inference Optimization with EENet

GTDLBench

Benchmarking Deep Learning Frameworks

EMO

Efficient Multi-Object Tracking for Edge devices

DP-Ensemble

Diversity Optimized Ensemble

STDLens

Lisa

This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)

DP_modelpublishing

GTAttackPod

Deep neural networks (DNNs) have demonstrated impressive performance on many challenging machine learning tasks. However, DNNs are vulnerable to adversarial inputs generated by adding maliciously crafted perturbations to the benign inputs. As a growing number of attacks have been reported to generate adversarial inputs of varying sophistication, the defense-attack arms race has been accelerated. This project collects state-of-the-art attack algorithms and organizes them with a easy-to-use interface.

EVA

Fast Edge Video Analytics

ZipZap

Perception-Poisoning

Perception Poisoning Attacks in Federated Learning

Booster

This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation".

DLForecast

Graph mining of the bitcoin transaction data for tasks such as transaction prediction.

HQ-Ensemble

Hierarchical Ensemble Pruning

Valet

Efficient Orchestration of Host and Remote Shared Memory for Memory Intensive Workloads

HeteRobust

recap

Code for CVPR24 Paper - Resource-Efficient Transformer Pruning for Finetuning of Large Models

MSJE

MSJE Pytorch implementation

membership_vulnerability

GTModelZoo

ModelCloak

Code for ICDM 2023 Model Cloaking against Gradient Leakage

Jupyter Notebook

MD-CNN

Network Code for Multi-Dimension Convolutional Neural Network for Bug Localization

GRING-App-Face_Exp_recog

G-RING application : Face Expression Recognition Federated Learning

FUSE

Robust Object Detection Fusion Against Deception

GRING-App-Disease_Classification

G-RING application : Implementation of disease classification federated learning task on G-RING

PFT

XEnsemble-1.0

Code for the XEnsemble Robust Deep Learnning project

gt-mobisim

Simulator for generating mobility traces and query traces for large numbers of mobile agents moving in a road network.

LRBenchPlusPlus

Jupyter Notebook

GRING

TripleBit

TripleBit, a fast and compact system for large scale RDF graph. This is a mirror of https://github.com/CGCL-codes/TripeBit.

SEJE

SEJE Pytorch implementation

llm-topla

Jupyter Notebook