BlockBlast reimplementation + RL agents (DQN, PPO, PPO+Action Masking, DQN+Action Masking, Random)
-
Updated
Apr 25, 2025 - Python
#
action-masking
Here are 12 public repositories matching this topic...
This repository contains code for the paper "Multi-agent reinforcement learning with action masking for uav-enabled mobile communications" which has been accepted for publishing in IEEE Transactions on Machine Learning in Communications and Networking.
uav trajectory-optimization heterogeneous multiagent-reinforcement-learning non-orthogonal-multiple-access action-masking
-
Updated
Dec 20, 2024 - Jupyter Notebook
Source code of “Agile Reinforcement Learning for Real-Time Task Scheduling in Edge Computing” (CAIAC 2025)
reinforcement-learning embedded-systems embedded-devices task-scheduler real-time-systems scheduling-algorithms edge-computing task-scheduling tiny-ml real-time-applications action-masking informed-exploration
-
Updated
Mar 12, 2026 - Python
My MSc project on applying, tuning and modifying the PPO and A2C algorithms to Pettingzoo MARL library two player poker game
-
Updated
Nov 8, 2023 - Python
Code for hierarchical signal coordination using hybrid model-based and RL approach.
-
Updated
Aug 13, 2025 - Python
Bot Pokémon Gen 1 (Random Battle Showdown) entraîné en RL avec MaskablePPO, imitation + curriculum + self-play ; suivi MLflow.
python pokemon reinforcement-learning pytorch game-ai gymnasium curriculum-learning ppo mlflow stable-baselines3 sb3-contrib action-masking poke-env maskable-ppo
-
Updated
May 13, 2026 - TypeScript
Neuro-symbolic RL agent that learns to pentest networks it has never seen — GPT-4o compiles CVE preconditions into a Z3 action mask over a GraphSAGE PPO policy. Zero-shot attack-graph transfer, negatives disclosed.
research reinforcement-learning cybersecurity penetration-testing smt-solver autonomous-agents ppo graphsage attack-graph graph-neural-network neuro-symbolic z3-solver llm nasim action-masking netwrok-attack-simulation
-
Updated
Jun 4, 2026 - Python
숫자 퍼즐 ‘사과 게임’을 pygame으로 구현하고, Gymnasium 환경에서 PPO·DQN·Monte Carlo 에이전트를 학습·실행하며 사람 vs PPO 대결까지 지원합니다.
python reinforcement-learning pygame puzzle-game dqn tensorboard gymnasium ppo stable-baselines3 action-masking
-
Updated
Mar 14, 2026 - Python
Board game agent learning strategy through PPO self-play over 5,000 episodes. 3-layer network (256->128->64), action masking for valid moves. Achieves 78% win rate vs random opponent, up from 56% at training start. 100% valid move rate maintained throughout.
-
Updated
Sep 22, 2025 - Jupyter Notebook
RL agent learns to generate drug-like molecules token-by-token in SMILES notation using PPO/SAC with optional action masking, LSTM policy, and RDKit-based multi-objective scoring (QED, SA score, LogP, Tanimoto similarity).
reinforcement-learning cheminformatics lstm drug-discovery rdkit multi-objective-optimization sac gymnasium ppo de-novo-design action-masking
-
Updated
May 3, 2026 - Python
Safe reinforcement learning with PPO-based action masking and penalty methods in MiniGrid Lava environments.
-
Updated
May 7, 2026 - Python
Unofficial Stable-Baselines3 extension package with MaskableRecurrentPPO.
python reinforcement-learning deep-reinforcement-learning pytorch lstm sac gymnasium ppo recurrent-ppo stable-baselines3 sb3-contrib action-masking maskable-ppo
-
Updated
Jun 24, 2026 - Python
Improve this page
Add a description, image, and links to the action-masking topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the action-masking topic, visit your repo's landing page and select "manage topics."