taner45 / advanced-reinforcement-learning Goto Github PK
View Code? Open in Web Editor NEWThis project forked from jaavad/advanced-reinforcement-learning
Explored reinforcement learning in-depth, covering key concepts like MDP, TD, Q-learning, SARSA, and MCTS. Advanced into Deep RL with DQN, Policy Gradient, and actor-critic methods (REINFORCE, DDPG, PPO). Explored Partially RL, Multi-agent RL, and Representation Learning. Applied RL in Robotics, engaging in coding exercises throughout the course.