Deep reinforcement learning-based air-to-air combat maneuver generation in a realistic environment

JH Bae, H Jung, S Kim, S Kim, YD Kim - IEEE Access, 2023 - ieeexplore.ieee.org
Artificial intelligence is becoming increasingly important in the air combat domain. Most air
combat research now assumes that all aircraft information is known. In practical applications …

Informed POMDP: Leveraging additional information in model-based RL

G Lambrechts, A Bolland, D Ernst - arXiv preprint arXiv:2306.11488, 2023 - arxiv.org
In this work, we generalize the problem of learning through interaction in a POMDP by
accounting for eventual additional information available at training time. First, we introduce …

CEMDQN: Cognitive-inspired episodic memory in deep Q-Networks

S Srivastava, H Rathore, K Tiwari - 2023 International Joint …, 2023 - ieeexplore.ieee.org
Reinforcement learning in the field of artificial intelligence has seen tremendous advances
in recent years, but there are still several limitations standing in the way of its wider practical …

Observation-Time-Action Deep Stacking Strategy: Solving Partial Observability Problems with Visual Input

K Jiang, Q Wang, Y Xu, H Deng - 2024 International Joint …, 2024 - ieeexplore.ieee.org
Reinforcement learning tasks that involve visual input continue to pose a challenge when it
comes to partial observability problems. Although prior research has introduced methods …