Deep Reinforcement Learning
Deep reinforcement learning (DRL) aims to train agents to make optimal decisions in complex environments by learning through trial and error. Current research focuses on improving DRL's robustness, sample efficiency, and interpretability, often employing architectures like Proximal Policy Optimization (PPO), deep Q-networks (DQNs), and graph neural networks (GNNs) to address challenges in diverse applications such as robotics, game playing, and resource management. The resulting advancements have significant implications for various fields, enabling the development of more adaptable and efficient autonomous systems across numerous domains.
Papers
Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector Quantization
Tung M. Luu, Thanh Nguyen, Tee Joshua Tian Jin, Sungwoon Kim, Chang D. Yoo
Latent Action Priors From a Single Gait Cycle Demonstration for Online Imitation Learning
Oliver Hausdörfer, Alexander von Rohr, Éric Lefort, Angela Schoellig
Spatial-aware decision-making with ring attractors in reinforcement learning systems
Marcos Negre Saura, Richard Allmendinger, Theodore Papamarkou, Wei Pan
Realizable Continuous-Space Shields for Safe Reinforcement Learning
Kyungmin Kim, Davide Corsi, Andoni Rodriguez, JB Lanier, Benjami Parellada, Pierre Baldi, Cesar Sanchez, Roy Fox
Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL
Ghada Sokar, Johan Obando-Ceron, Aaron Courville, Hugo Larochelle, Pablo Samuel Castro
Finding path and cycle counting formulae in graphs with Deep Reinforcement Learning
Jason Piquenot, Maxime Bérar, Pierre Héroux, Jean-Yves Ramel, Romain Raveaux, Sébastien Adam
Life, uh, Finds a Way: Systematic Neural Search
Alex Baranski, Jun Tani