Reinforcement Learning for Robotics
Apply reinforcement learning (RL) and deep RL algorithms to train robots to perform complex tasks and make optimal decisions in real-time. Learn about policies, rewards, and simulation-to-real transfer.
22 courses
Master the fundamentals of training intelligent agents using Python, PyTorch, and modern reinforcement learning algorithms like A2C and DDPG.
Build a foundation in artificial intelligence by creating autonomous agents for games like Snake and mazes using reinforcement learning techniques.
Build and train intelligent AI agents from scratch using PyTorch and Gymnasium to solve complex decision-making and control tasks.
Understand the principles of neural networks and reward-based learning to build a solid foundation in modern artificial intelligence.
Learn to build intelligent agents that solve complex tasks by combining deep neural networks with reinforcement learning principles.
Build a solid foundation in reinforcement learning by implementing classic Q-learning, Deep Q-Networks, and policy gradient algorithms using modern Python libraries.
Learn how agents interact with environments using Q-learning, policy gradients, and modern feedback loops through clear text-based explanations.
Learn to design and train intelligent agents for complex control tasks using modern policy gradients and trust region methods.
Build a strong foundation in neural networks, modern deep learning architectures, and reinforcement learning algorithms through structured written explanations and code.
Master the core principles of reinforcement learning and build your first intelligent agents using clean, modern PyTorch code.
Build intelligent decision-making agents and master modern reinforcement learning algorithms through step-by-step written explanations and code tutorials.
Learn how to train intelligent game agents using generative adversarial imitation learning (GAIL) to mimic human playstyles without complex reward engineering.
Learn to generate structured text by combining sequence generative adversarial networks with reinforcement learning techniques for sequence modeling.
Learn how to reconstruct reward functions from expert behavior to train intelligent agents and align modern generative AI models.
Learn to write clean algorithms that generate customizable, sparse mazes by adjusting path density and trimming dead ends for engaging puzzle designs.
Learn to use coding large language models and the Eureka framework to autonomously design, evaluate, and refine reward functions for reinforcement learning agents.
Learn to train intelligent game characters using reinforcement learning, neural networks, and generative adversarial imitation learning through structured written guides.
Build a solid foundation in reinforcement learning by understanding core algorithms and applying them to decision-making problems through clear written guides.
Understand the core theories of reinforcement learning and build intelligent decision-making agents using clean, modern Python code.
Learn the core concepts of clustering, neural networks, and decision-making agents to build a strong foundation in modern artificial intelligence.
Showing 20 of 22 courses