Skip to content
conftrace_

policy switching

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

reference-advantage decomposition (1) reward cost trade-off (1) near-accident scenario (1) federated q-learning (1) reward optimization (1) temporal logic constraint (1) communication cost (1) regret (1) safe reinforcement learning (1) reward maximization (1)

Papers

Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning AAAI 2025 Federated Q-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost ICLR 2025 Probabilistic Satisfaction of Temporal Logic Constraints in Reinforcement Learning via Adaptive Policy-Switching L4DC 2025 Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving RSS 2020