Paper Session VII

• Filip Georgiev, Kalle Timperi, Bașak Sakçak, and Steven LaValle, “Relating Reinforcement Learning to Dynamic Programming-Based Planning”
• Xinhuan Sang, Abdelrahman Abdelgawad, and Roberto Tron, “Composable Model-Free RL for Navigation with Input-Affine Systems”
• Thong Quoc Huynh, Oren Salzman, and Neil Dantam, “Environmental-Computational Epistemic Agents: Observations for Optimal Decisions”
• Alkesh Kumar Srivastava, George Kontoudis, Donald Sofge, and Michael Otte, “Bayesian Networks for Path-Based Sensors: Gathering Information and Path Planning in Communication Denied Environments”