 Interpretable and Explainable Logical Policies via Neurally Guided
Symbolic AbstractionNeural Information Processing Systems (NeurIPS), 2023 |
 Neural Episodic Control with State AbstractionInternational Conference on Learning Representations (ICLR), 2023 |
 Computationally Efficient Reinforcement Learning: Targeted Exploration
leveraging Simple RulesIEEE Conference on Decision and Control (CDC), 2022 |
 Flexible Attention-Based Multi-Policy Fusion for Efficient Deep
Reinforcement LearningNeural Information Processing Systems (NeurIPS), 2022 |
 GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic
SynthesisNeural Information Processing Systems (NeurIPS), 2022 |
 PMIC: Improving Multi-Agent Reinforcement Learning with Progressive
Mutual Information CollaborationInternational Conference on Machine Learning (ICML), 2022 |
 Efficient Use of heuristics for accelerating XCS-based Policy Learning
in Markov GamesSwarm and Evolutionary Computation (Swarm Evol. Comput.), 2020 |
