Citation :

Ruchi Agarwal, 2023. "Comparative Study of Neural Network Architectures in Deep Reinforcement Learning" ESP International Journal of Advancements in Computational Technology (ESP-IJACT)  Volume 1, Issue 2: 85-88.

Abstract :

This article presents a comprehensive comparative analysis of various neural network architectures employed in deep reinforcement learning (DRL). We examine the efficacy, computational complexity, and scalability of different architectures, including feedforward networks, convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformer-based models. Our study encompasses both value-based and policy-gradient methods, evaluating their performance across a spectrum of environments and tasks. The findings illuminate the strengths and limitations of each architecture, providing insights for researchers and practitioners in the field of DRL.

References :

[1] Mnih, V., et al. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529-533.

[2] Levine, S., et al. (2016). End-to-end training of deep visuomotor policies. The Journal of Machine Learning Research, 17(1), 1334-1373.

[3] Kober, J., Bagnell, J. A., & Peters, J. (2013). Reinforcement learning in robotics: A survey. The International Journal of Robotics Research, 32(11), 1238-1274.

[4] Mnih, V., et al. (2013). Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602.

[5] Schulman, J., et al. (2017). Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347.

[6] Haarnoja, T., et al. (2018). Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. arXiv preprint arXiv:1801.01290.

[7] Brockman, G., et al. (2016). OpenAI Gym. arXiv preprint arXiv:1606.01540.

[8] Beattie, C., et al. (2016). DeepMind Lab. arXiv preprint arXiv:1612.03801.

[9] Wang, Z., et al. (2016). Dueling network architectures for deep reinforcement learning. In International conference on machine learning (pp. 1995-2003). PMLR.

[10] Szegedy, C., et al. (2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1-9).

[11] He, K., et al. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).

[12] Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.

[13] Cho, K., et al. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078.

[14] Vaswani, A., et al. (2017). Attention is all you need. In Advances in neural information processing systems (pp. 5998-6008).

[15] Parisotto, E., et al. (2020). Stabilizing transformers for reinforcement learning. In International Conference on Machine Learning (pp. 7487-7498). PMLR.

Keywords :

Deep Reinforcement Learning, Neural Network Architectures, Feed Forward Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks, Long Short-Term Memory Networks, Attention Mechanisms, Transformers.