← Search

Jiajing Ling

2 accepted papers

2025

Leveraging Constraint Violation Signals for Action Constrained Reinforcement Learning

AAAI 2025technical

In many RL applications, ensuring an agent's actions adhere to constraints is crucial for safety. Most previous methods in Action-Constrained Reinforcement Learning (ACRL) employ a projection layer after the policy network to correct the action. However projection-based methods suffer from issues li…

2023

FlowPG: Action-constrained Policy Gradient with Normalizing Flows

NeurIPS 2023poster

Action-constrained reinforcement learning (ACRL) is a popular approach for solving safety-critical and resource-allocation related decision making problems. A major challenge in ACRL is to ensure agent taking a valid action satisfying constraints in each RL step. Commonly used approach of using a pr…