Proposes HAD-MFC framework that decouples upper-level vulnerable agent selection from lower-level adversarial policy learning in large-scale MARL using Fenchel-Rockafellar transform and MDP reformulation with provable optimality preservation.
Reinforcement Learning via Fenchel-Rockafellar Duality
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
Presents the first algorithm to identify an ε-optimal policy in robust constrained MDPs via epigraph form and bisection search with Õ(ε^{-4}) robust policy evaluations.
TRAM is a test-time mixture method that scores and composes risk-neutral source policies using reward and occupancy-based risk to achieve new reward-risk tradeoffs without parameter updates.
Offline RL promises to extract high-utility policies from static datasets but faces fundamental challenges that current methods only partially address.
citing papers explorer
-
Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning
Proposes HAD-MFC framework that decouples upper-level vulnerable agent selection from lower-level adversarial policy learning in large-scale MARL using Fenchel-Rockafellar transform and MDP reformulation with provable optimality preservation.
-
Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form
Presents the first algorithm to identify an ε-optimal policy in robust constrained MDPs via epigraph form and bisection search with Õ(ε^{-4}) robust policy evaluations.
-
TRAM: Test-Time Risk Adaptation with Mixture of Agents
TRAM is a test-time mixture method that scores and composes risk-neutral source policies using reward and occupancy-based risk to achieve new reward-risk tradeoffs without parameter updates.
-
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
Offline RL promises to extract high-utility policies from static datasets but faces fundamental challenges that current methods only partially address.