tutorials.99_examples.rst

Usage Examples

In the following, we collect the links to MushroomRL scripts showing examples for most approaches available in MushroomRL.

The examples can be all found in the examples folder in the MushroomRL repository.

Finite MDPs with Temporal Difference

• Simple Chain
• Double Chain
• Grid World
• Taxi

TD with function approximation

• Mountain Car with SARSA
• Puddle World with SARSA
• CarOnHill with FQI
• CartPole with LSPI

Classical Policy Search and Actor-Critic

• LQR with Policy Gradient
• Pendulum with Stochastic Actor-Critic
• Pendulum with Deterministic Actor-Critic

Black Box Optimization

• LQR with BBO
• Segway with BBO
• Ship Steering with BBO

Deep Critic-Only

• Acrobot with DQN
• Minigrid with DQN
• Atari

Deep Actor-Critic

• Acrobot with A2C
• Pendulum with A2C
• Pendulum with Trust Region approaches
• Pendulum with Deterministic Gradient
• Pendulum with SAC

Continuos Control From Pixels

• Walker (Stand Task) from Pixel
• Walker (Stand Task) from Pixel and Shared Network

Others Examples (Environment and Tools)

• Using Dataset Plotting callback and State Normalization
• Habitat Navigation Task with DQN
• Habitat Rearrange Task with SAC from Pixel and Shared Network
• iGibson with DQN