tic-tac-toe blackjack q-learning game-theory minimax-algorithm multi-armed-bandit softmax monte-carlo-methods bellman-ford-algorithm evolutionary-game-theory sarsa-learning temporal-difference-learning markov-decision-process softmax-policy cournot-competition instigation-game applied-game-theory

reinforcement-learning rl ucb multi-armed-bandits bandits softmax regret bandit-algorithms regret-minimization softmax-policy bernoulli-bandit gaussian-bandit