Assignment
Budget: $10 – $30 USD
Que.1 Consider the following grid environment. Starting from any unshaded square, you can
move up, down, left, or right. Actions are deterministic and always succeed (e.g., going
left from state 1 goes to state 0) unless they will cause the agent to run into a wall. The
thicker edges indicate walls and attempting to move in the direction of a wall results in
staying in the same square. Taking any action from the green target square (no. 5) earns a
reward of +5 and ends the episode. Otherwise, each move is associated with some
?????? ? ∈ {−1, 0, +1}. Assume the discount factor ? = 1 unless otherwise specified.
Que. 2 Implement value iteration and policy iteration for the Taxi Driver environment from
OpenAI Gym (https://gym.openai.com/envs/Taxi-v3/). We have provided custom versions
of this environment in the starter code.
move up, down, left, or right. Actions are deterministic and always succeed (e.g., going
left from state 1 goes to state 0) unless they will cause the agent to run into a wall. The
thicker edges indicate walls and attempting to move in the direction of a wall results in
staying in the same square. Taking any action from the green target square (no. 5) earns a
reward of +5 and ends the episode. Otherwise, each move is associated with some
?????? ? ∈ {−1, 0, +1}. Assume the discount factor ? = 1 unless otherwise specified.
Que. 2 Implement value iteration and policy iteration for the Taxi Driver environment from
OpenAI Gym (https://gym.openai.com/envs/Taxi-v3/). We have provided custom versions
of this environment in the starter code.