A rate-distortion based switching strategy for adaptive state-action abstractions in RL decomposes value error into Bellman residual and bisimulation metric terms to achieve near-optimal performance under lossy compression in tabular settings.
Efficient Solution Algorithms for Factored MDPs
3 Pith papers cite this work, alongside 156 external citations. Polarity classification is still indexing.
3
Pith papers citing it
156
external citations · external index
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 3representative citing papers
Reinforcement learning agents for network intrusion response can be more effective than heuristic policies in a cyber range, but their success depends on attacker strategy and real-world noise like simulated user activity.
citing papers explorer
-
Adaptive state-action abstractions via rate-distortion
A rate-distortion based switching strategy for adaptive state-action abstractions in RL decomposes value error into Bellman residual and bisimulation metric terms to achieve near-optimal performance under lossy compression in tabular settings.
-
A Cyber Range Evaluation of Autonomous Network Incident Response Agents
Reinforcement learning agents for network intrusion response can be more effective than heuristic policies in a cyber range, but their success depends on attacker strategy and real-world noise like simulated user activity.
- Probabilistic Hazard Analysis Framework with Stochastic Optimal Control for Deteriorating Civil Infrastructure Systems