(Also, if you don’t have deep learning background but want to learn to solve problems like these, please apply for our Fellowship⁠(opens in a new window) program!)

⭐ Train an LSTM to solve the XOR problem: that is, given a sequence of bits, determine its parity. The LSTM⁠(opens in a new window) should consume the sequence, one bit at a time, and then output the correct answer at the sequence’s end. Test the two approaches below:

⭐ Implement a clone of the classic Snake⁠(opens in a new window) game as a Gym⁠(opens in a new window) environment, and solve it with a reinforcement learning⁠(opens in a new window) algorithm of your choice. Tweet⁠(opens in a new window) us videos of the agent playing. Were you able to train a policy that wins the game?

⭐⭐ Slitherin’. Implement and solve a multiplayer clone of the classic Snake⁠(opens in a new window) game (see slither.io⁠(opens in a new window) for inspiration) as a Gym⁠(opens in a new window) environment.