- Reviewed Version (pdf): https://openreview.net/references/pdf?id=GiSjomqM25
- Keywords: Deep Reinforcement learning, Policy architectures
- Abstract: While improvements in deep learning architectures have played a crucial role in improving the state of supervised and unsupervised learning in computer vision and natural language processing, neural network architecture choices for reinforcement learning remain relatively under-explored. We take inspiration from successful architectural choices in computer vision and generative modeling, and investigate the use of deeper networks and dense connections for reinforcement learning on a variety of simulated robotic learning benchmark environments. Our findings reveal that current methods benefit significantly from dense connections and deeper networks, across a suite of manipulation and locomotion tasks, for both proprioceptive and image-based observations. We hope that our results can serve as a strong baseline and further motivate future research into neural network architectures for reinforcement learning. The project website is at this link https://sites.google.com/view/d2rl-anonymous/home
- One-sentence Summary: Introducing dense architectures in the policy and value function in deep reinforcement learning can significantly improve performance in state and image-based RL.
- Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics