RL Examples

The following is a list of reinforcement learning examples a user can go through

• Some basic concepts (Python)
  • Import statements
  • Driver code
  • Results
• TD Examples (Python)
  • Double Q-learning on CartPole-v0 (Python)
  • QLearning on CartPole-v0 (Python)
  • Q-learning on CliffWalking-v0 (Python)
  • QLearning on FrozenLake-v0 (Python)
  • SARSA algorithm on CartPole-v0 (Python)
  • Semi-gradient SARSA on MountainCar-v0 (Python)
• Some basic concepts (C++)
  • Include files
  • Driver code
  • Results
• Iterative policy evaluation on FrozenLake-v0 (C++)
  • Code
  • Results
• Iterative policy evaluation on FrozenLake-v0 (Python)
• Policy iteration on FrozenLake-v0 (C++)
  • Code
  • Results
• Policy iteration on FrozenLake-v0 (Python)
• Value iteration on FrozenLake-v0 (C++)
  • Code
  • Results
• Value iteration on FrozenLake-v0 (Python)
• SARSA on CliffWalking-v0 (C++)
  • Overview
  • Code
  • Results
• Q-learning on CliffWalking-v0 (C++)
  • Overview
  • Code
  • Results
• REINFORCE on CartPole-v0 (C++)
  • Overview
  • Code
  • Results
• Q-learning CartPole-v0 (C++)
• Double Q-learning on CartPole-v0
  • Overview
  • Code
  • Results
• Webots controller development-getting started
  • Start a controller
  • Reading sensors
  • Using actuators
  • Terminate a controller
• Simple Q-learning based controller for epuck robot