1. 9.5 Towards A Unified Agent with Foundation Models
   • Authors: Norman Di Palo, Arunkumar Byravan, Leonard Hasenclever, Markus Wulfmeier, Nicolas Heess, Martin Riedmiller
   • Abstract: Investigates how to embed and leverage abilities of Language Models and Vision Language Models in Reinforcement Learning (RL) agents.
2. 9.4 STRAPPER: Preference-based Reinforcement Learning via Self-training Augmentation and Peer Regularization
   • Authors: Yachen Kang, Li He, Jinxin Liu, Zifeng Zhuang, Donglin Wang
   • Abstract: Proposes a new approach to Preference-based reinforcement learning (PbRL), presenting a novel method for penalty regularization for reward model memorizing uninformative labels reaching confident predictions.
3. 9.3 XSkill: Cross Embodiment Skill Discovery
   • Authors: Mengda Xu, Zhenjia Xu, Cheng Chi, Manuela Veloso, Shuran Song
   • Abstract: Presents XSkill, an imitation learning framework that learns skill prototypes from unlabeled human and robot manipulation videos, then transfers these skills to robot actions and composes them to accomplish unseen tasks.
4. 9.2 Reinforcement Learning for Credit Index Option Hedging
   • Authors: Francesco Mandelli, Marco Pinciroli, Michele Trapletti, Edoardo Vittori
   • Abstract: Applies a state of the art algorithm, the Trust Region Volatility Optimization (TRVO) on finding optimal hedging strategy of a credit index option. The derived strategy outperforms the standard Black & Scholes delta hedge.
5. 9.1 Deep Reinforcement Learning for ESG financial portfolio management
   • Authors: Eduardo C. Garrido-Merchán, Sol Mora-Figueroa-Cruz-Guzmán, María Coronado-Vaca
   • Abstract: Investigates the application of Deep Reinforcement Learning (DRL) for Environment, Social, and Governance (ESG) financial portfolio management and finds DRL agent within the ESG-regulated market outperforms standard DJIA market setup.