https://www.chenk.top/en/tags/experience-replay/Recent content in Experience Replay on Chen Kai BlogHugoenWed, 06 Aug 2025 09:00:00 +0000https://www.chenk.top/en/reinforcement-learning/02-q-learning-and-dqn/Wed, 06 Aug 2025 09:00:00 +0000https://www.chenk.top/en/reinforcement-learning/02-q-learning-and-dqn/<p>In December 2013, a small DeepMind team uploaded a paper to arXiv with a striking claim: a single neural network, trained from raw pixels and the score, learned to play seven Atari games — and beat the previous best on six of them. No game-specific features. No hand-coded heuristics. The same architecture for Pong, Breakout, and Space Invaders. The algorithm was <strong>Deep Q-Network (DQN)</strong>, and it kicked off the deep reinforcement learning era.</p>