This repository describes the 'Deep Q-Network'. For the improved algorithms, 'Dueling DQN', which divide the action-value function (Q(s, a)) into advantage function (A(a)) and state-value function (v(s)) and 'Double DQN', which has two neural network (primary NN and target NN) will be uploaded as well.
This repository describes the 'Deep Q-Network'. For the improved algorithms, 'Dueling DQN', which divide the action-value function (Q(s, a)) into advantage function (A(a)) and state-value function (v(s)) and 'Double DQN', which has two neural network (primary NN and target NN) will be uploaded as well.
This repository describes the 'Deep Q-Network'. For the improved algorithms, 'Dueling DQN', which divide the action-value function (Q(s, a)) into advantage function (A(a)) and state-value function (v(s)) and 'Double DQN', which has two neural network (primary NN and target NN) will be uploaded as well.