a high-level framework for solving sequential decision-making problems. An RL agent navigates an environment by taking actions based on some observations, receiving rewards as a result. Most RL algorithms work by maximizing the expected total rewards an agent collects in a trajectory, e.g., during one in-game round. - Deep Reinforcement Learning With TensorFlow 2.1

see also

• Apprentissage par renforcement #2 - Exploration et Exploitation
  • Value Function - backtracking from final state
  • Premier Jeu - jeux des allumettes - value fonction simple a apprendre
  • Q-Learning - equation de bellman - definition recursive de la q-function
  • Deep Q-Learning
• If you want to try… - from Mastering a Pod Racing AI Competition with Nash-DQN