🤖 Phase 4 — Deep Reinforcement Learning

Combine neural networks with RL for high-dimensional control tasks.

Topics

• Deep Q-Network (DQN) and Stability Tricks
• Double DQN, Dueling DQN, Prioritized Replay
• Continuous Control: DDPG, TD3
• PPO (Proximal Policy Optimization)
• SAC (Soft Actor-Critic)

Mini Projects

• Atari Pong (DQN)
• LunarLanderContinuous-v2 (DDPG / PPO)

📁 Source folder:
04-DeepRL