Markov Models
BQ-NCO: Bisimulation Quotienting for Efficient Neural Combinatorial Optimization
Despite the success of neural-based combinatorial optimization methods for end-to-end heuristic learning, out-of-distribution generalization remains a challenge.
Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning Jianzhun Shao, Y un Qu
MARL in real scenarios is still challenging due to the same safety and efficiency concerns in single-agent setting, then it is worth conducting investigation for offline RL in multi-agent setting.
Optimal Convergence Rate for Exact Policy Mirror Descent in Discounted Markov Decision Processes
Our study of the convergence of PMD avoids the use of the performance difference lemma, which leads to a direct analysis of independent interest.
ODE-based Recurrent Model-free Reinforcement Learning for POMDPs
In partially observable (PO) environments, how to infer unseen information from raw observations puzzled the agents.
