Markov Models
Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization Xiangsen Wang
Despite some success in the single-agent setting, offline multi-agent RL (MARL) remains to be a challenge. The large joint state-action space and the coupled multi-agent behaviors pose extra complexities for offline policy optimization.
On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes
Risk-averse reinforcement learning (RL) seeks to provide a risk-averse policy for high-stakes real-world decision problems. These high-stake domains include autonomous driving (Jin et al., 2019; Sharma et al., 2020), robot collision avoidance (Ahmadi et al., 2021; Hakobyan and Y ang, 2021),
9dc5accb1e4f4a9798eae145f2e4869b-Supplemental-Conference.pdf
Both challenges involve modeling long-term dependencies.
Pairwise Causality Guided Transformers for Event Sequences
Such statements embed the notion of pairwise causality and can be better paraphrased as'occurrences of event type Z
Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations
In Reinforcement Learning (RL), an agent engages with an environment in a sequential manner.
Active Observing in Continuous-time Control
The decision-maker's observing policy must be timely
Active Observing in Continuous-time Control
The decision-maker's observing policy must be timely