#Deep Reinforcement Learning

Logo of mit-deep-learning
mit-deep-learning
Explore the MIT Deep Learning repository, which features a well-rounded set of tutorials focused on neural network basics, driving scene segmentation, and advanced techniques like generative adversarial networks. The DeepTraffic competition further enriches your learning experience by offering practical challenges in deep reinforcement learning. This evolving resource, aligned with MIT's ongoing courses, serves as a beneficial tool for newcomers and experienced practitioners in artificial intelligence.
Logo of Deep_reinforcement_learning_Course
Deep_reinforcement_learning_Course
This free course offers a comprehensive exploration of Deep Reinforcement Learning, focusing on both theory and practice. It guides the use of popular libraries like Stable Baselines3 and CleanRL, and delves into training agents in various environments such as Minecraft and Doom. The course also facilitates effortless publication of trained agents and provides opportunities to compete in AI challenges, making it an ideal avenue for advancing in AI development.
Logo of pytorch-rl
pytorch-rl
Explore a broad range of sophisticated deep reinforcement learning algorithms in Pytorch, emphasizing continuous action spaces. Efficiently train on CPUs or GPUs and straightforwardly evaluate with OpenAI Gym. This repository includes various model-free and model-based RL algorithms, offering techniques like DDPG, PPO, and soft actor-critic, in addition to experimental methods such as prioritized experience replay. Flexible for extensions, it accommodates environments from classic games to complex robotic tasks.
Logo of awesome-deep-rl
awesome-deep-rl
Discover the latest in Deep Reinforcement Learning (DRL) through this detailed guide, covering foundational concepts, unsupervised techniques, multi-agent frameworks, and the fusion of policy and value-based approaches. Updated with recent innovations like HILP and EDDICT, this resource provides essential insights into RL framework progressions and applications. It offers a balanced overview of current research and practical applications without unnecessary embellishments.
Logo of phillip
phillip
Explore an SSBM AI project leveraging deep reinforcement learning. Compatible with Ubuntu, OSX, and Windows, it necessitates a custom Dolphin emulator, SSBM iso, and Python 3. Although inactive, the project offers trained agents and local training options. For community support and video content, visit Discord or YouTube.
Logo of DeepLearningFlappyBird
DeepLearningFlappyBird
The DeepLearningFlappyBird project employs the Deep Q-Network algorithm to train AI for Flappy Bird, using convolutional neural networks to analyze pixel data for gameplay optimization. Featuring key reinforcement learning techniques, the project integrates TensorFlow, pygame, and OpenCV-Python. Step-by-step guidance is provided to build a learning architecture that masters the game through state-action value functions and adaptive training, like ε-greedy policy and mini-batch sampling. Discover advancements in AI game strategy through detailed implementation methods.
Logo of cleanrl
cleanrl
CleanRL delivers straightforward and scalable deep reinforcement learning in single-file formats, facilitating ease of understanding for developers and researchers. It supports a wide array of algorithms and games, enhancing workflow with AWS and Weights & Biases integration for seamless experiment management both locally and on the cloud. The platform also offers valuable features like Tensorboard logging, gameplay recording, and comprehensive benchmarking.
Logo of Autonomous-Driving-in-Carla-using-Deep-Reinforcement-Learning
Autonomous-Driving-in-Carla-using-Deep-Reinforcement-Learning
This project uses CARLA simulation and Deep Reinforcement Learning with Proximal Policy Optimization to improve autonomous driving capabilities. It trains agents in hyper-realistic urban environments, leveraging a Variational Autoencoder for efficient learning. By focusing on continuous state and action spaces, it aims to provide reliable autonomous navigation on predetermined routes, offering a comprehensive end-to-end driving solution.
Logo of rainbow-is-all-you-need
rainbow-is-all-you-need
Discover how to transition from DQN to Rainbow in this deep reinforcement learning guide, featuring theoretical insights and practical implementations. Suitable for beginners and experienced users, this tutorial is accessible via Google Colab, even on mobile devices. Essential topics include DoubleDQN, Prioritized Experience Replay, and NoisyNet. Contributions are welcomed through pull requests or issues, emphasizing practical application for mastering AI-driven strategies.
Logo of ElegantRL
ElegantRL
ElegantRL provides a cloud-native deep reinforcement learning framework optimized for scalability, elasticity, and lightweight performance. Its architecture supports major DRL algorithms such as DDPG, TD3, and PPO on platforms like Isaac Gym and OpenAI Gym. Utilizing parallelism, it offers improved performance and stability over Ray RLlib and Stable Baselines 3, reducing training resources. This makes it adaptable for various environments and applications, from single-agent to multi-agent scenarios.
Logo of DouZero
DouZero
DouZero, developed by Kwai Inc.'s AI Platform, uses deep reinforcement learning to excel at DouDizhu, a popular Chinese card game. By integrating techniques like Deep Monte Carlo, it tackles complex action spaces and imperfect information efficiently. This project provides source code and an online demo, fostering research in AI applications with broad state spaces.
Logo of Reinforcement-Learning
Reinforcement-Learning
The project provides a thorough introduction to deep reinforcement learning, highlighting the integration of neural networks and reinforcement learning algorithms. It includes practical implementation of algorithms like Q-learning, PPO, and actor-critic using Python and PyTorch in environments such as OpenAI Gym and RoboSchool. It features content from renowned sources like DeepMind and UC Berkeley, equipping learners to address real-world challenges with advanced machine learning strategies. Suitable for individuals with foundational knowledge of Python, PyTorch, and basic deep learning.
Logo of awesome-multi-modal-reinforcement-learning
awesome-multi-modal-reinforcement-learning
Discover a curated selection of research papers on Multi-Modal Reinforcement Learning (MMRL), showcasing the latest advancements and core methodologies. This repository, regularly updated, enhances comprehension of visual and language integration within reinforcement learning, beneficial for researchers delving beyond standard RL boundaries. Explore diverse experimental environments and deepen your understanding of multimodal influences on RL mechanisms.
Logo of PhySO
PhySO
PhySO harnesses deep reinforcement learning to enhance symbolic regression in physics, focusing on dimensional analysis and class constraints. It performs reliably in noisy conditions and is validated on benchmarks such as SRBench. PhySO's design emphasizes efficiency with minimal dependencies, and its integration guides facilitate easy setup in various computational environments.
Logo of deep-rl-class
deep-rl-class
Discover the Deep Reinforcement Learning resources offered by Hugging Face, featuring detailed mdx files and notebooks aimed at enhancing understanding of AI methodologies. The course includes a structured syllabus and in-depth lectures suitable for those interested in advancing their study of AI. Access comprehensive resources provided by field experts to deepen your learning of reinforcement learning techniques.
Logo of Deep-RL-Keras
Deep-RL-Keras
The project provides modular implementations of essential deep reinforcement learning algorithms using Keras suitable for discrete and continuous action spaces. It features Actor-Critic approaches like A2C and A3C and Deep Q-Learning variations such as DDQN with prioritized experience replay and dueling networks. Requiring Keras 2.1.6 and OpenAI Gym, it facilitates efficient and scalable setups, with tools for visualization and monitoring through TensorBoard and Plotly, focusing on stability and exploration in complex environments.
Logo of drl-zh
drl-zh
This course provides a hands-on experience in deep reinforcement learning by guiding participants through building algorithms like DQN, SAC, and PPO from scratch. Learn to use tools such as Miniconda and Poetry in a streamlined coding environment with comprehensive resources for independent verification and learning.
Logo of easy-rl
easy-rl
Discover reinforcement learning fundamentals through materials by renowned educators such as Li Hongyi, Zhou Bo Lei, and Li Kejiao. This resource provides Chinese learners with comprehensive videos, supplementary materials, and practical projects, ideal for new students. Often referred to as the 'Mushroom Book', it offers a balanced approach to enhancing understanding in AI.