Implementations of Q-learning [1-4] in Farama’s Gymnasium environments.
Deep Q-Networks (DQN)
Double DQN
Dueling Double DQN
Prioritized Experience Replay
FARAMA’S GYMNASIUM
(https://gymnasium.farama.org)
[1] Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Riedmiller, M. (2013). Playing atari with deep reinforcement learning.(https://www.doi.org/10.48550/arXiv.1312.5602)
[2] Van Hasselt, Hado, Arthur Guez, and David Silver. "Deep reinforcement learning with double q-learning." Proceedings of the AAAI conference on artificial intelligence. Vol. 30. No. 1. 2016. (https://www.doi.org/10.48550/arXiv.1509.06461)
[3] Schaul, T., Quan, J., Antonoglou, I. & Silver, D. (2015). Prioritized Experience Replay Published at ICLR 2016 (https://www.doi.org/10.48550/arXiv.1511.05952)
[4] Ziyu Wang, Tom Schaul, Matteo Hessel, Hado Van Hasselt, Marc Lanctot, and Nando De Freitas. 2016. Dueling network architectures for deep reinforcement learning. In Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48 (ICML'16). JMLR.org, 1995–2003.(https://www.doi.org/10.48550/arXiv.1511.06581)