Bellman values for temporal logic tasks decompose into a graph of reach-avoid, avoid, and reach-avoid-loop equations solved by embedding the graph in a two-layer neural net (VDPPO) for safe high-dimensional control.
Iterative reachability estimation for safe reinforcement learning,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2verdicts
UNVERDICTED 2representative citing papers
A separate regulator module adaptively scales actions in RL to reduce constraint violations while preserving exploration, yielding up to 126x fewer violations and over 10x higher returns on Safety Gym tasks.
citing papers explorer
-
Bellman Value Decomposition for Task Logic in Safe Optimal Control
Bellman values for temporal logic tasks decompose into a graph of reach-avoid, avoid, and reach-avoid-loop equations solved by embedding the graph in a two-layer neural net (VDPPO) for safe high-dimensional control.
-
Constraint-Aware Reinforcement Learning via Adaptive Action Scaling
A separate regulator module adaptively scales actions in RL to reduce constraint violations while preserving exploration, yielding up to 126x fewer violations and over 10x higher returns on Safety Gym tasks.