Reinforcement Learning for Robotics

Apply advanced machine learning techniques to teach robots complex behaviors through trial and error. Implement reinforcement learning algorithms for tasks like locomotion, manipulation, and navigation.

41 courses

AI Development with Python: Generative AI and Reinforcement Learning

Build intelligent systems using Python and AWS while mastering prompt engineering, generative models, and autonomous agents.
★ 4.5 (1,578)

Practical Reinforcement Learning in Python: Build Intelligent AI Agents

Master the fundamentals of deep reinforcement learning and build custom intelligent agents using Python, TensorFlow, and Gymnasium.
★ 4.6 (1,290)

Deep Reinforcement Learning with Python: Train Virtual Agents with TD3

Master the foundations of reinforcement learning and implement the advanced TD3 algorithm in Python to train virtual agents to walk, run, and navigate complex environments.
★ 4.7 (1,367)

Augmented Random Search: Building High-Performance AI

Learn to implement efficient reinforcement learning models from scratch to solve complex tasks using the power of Augmented Random Search.
★ 4.4 (1,102)

Deep Reinforcement Learning: Implementing Research Papers in PyTorch and TensorFlow

Learn to translate complex AI research into functional code by building advanced agents for continuous control and decision-making tasks.
★ 4.3 (530)

Reinforcement Learning in Python: Build AI Agents with PyTorch and Gym

Learn to design, train, and evaluate intelligent AI agents from scratch using Python, PyTorch, and standard Gym simulation environments.
★ 4.3 (402)

Reinforcement Learning with Python for Beginners

Build and train intelligent agents to solve complex tasks and play games using modern Python libraries and core reinforcement learning principles.
★ 4.3 (164)

Robotics Simulation Fundamentals with Webots

Build a strong foundation in robotics by simulating and programming autonomous mobile robots using the Webots environment and modern Python control APIs.
★ 4.5 (78)

Machine Teaching for Autonomous AI Systems

Learn how to transfer human expertise to intelligent agents by structuring tasks, designing reward systems, and building autonomous control solutions.
★ 4.7 (47)

Deep Learning to AI Agents: Building Generative AI with MCP

Learn the fundamentals of deep learning, build autonomous AI agents, and implement the Model Context Protocol to connect models with external tools and data sources.
★ 4.3 (8)

Physical AI Foundations: Python and AI for the Real World

Discover how to connect Python-based AI to physical systems, sensor data, and smart devices through clear, step-by-step written explanations.
★ 5.0 (1)

AI Alignment: RLHF and Constitutional AI Explained

Understand how to build safer and more ethical AI models by applying Reinforcement Learning from Human Feedback and Constitutional AI principles.

Reinforcement Learning: GAIL for Imitation Learning

Understand how to apply Generative Adversarial Imitation Learning (GAIL) to build reinforcement learning agents that mimic expert behavior.

Learn Aldous-Broder Maze Generation

Master the Aldous-Broder algorithm to generate unbiased mazes, ideal for game development or computational art projects.

Building Reward Learning Agents

Learn to design, structure, and implement intelligent agents that adapt and learn from rewards, suitable for beginners.

Maze Generation with Simplified Prim's Algorithm

Master the logic of randomized maze generation by implementing a simplified version of Prim's algorithm and understanding how it differs from the classic graph approach.

Prim's Algorithm for Maze Creation

Master the fundamentals of Prim's Algorithm to generate unique and solvable maze structures.

Aldous-Broder Algorithm for Unbiased Maze Generation

Understand and apply the Aldous-Broder algorithm to generate unique and unbiased mazes, perfect for game development or simulations.

Imitation Learning with GAIL and PyBullet Gym

Understand and apply Generative Adversarial Imitation Learning (GAIL) to train agents in physics-based PyBullet Gym environments.

Maze Generation for Multisphere Grids

Master fundamental algorithms and data structures to design intricate, interconnected mazes across complex spherical surfaces.
Showing 20 of 41 courses