3 papers
cs.LG2025
LLM-Driven Composite Neural Architecture Search for Multi-Source RL State Encoding
Yu Yu, Qian Xie, Nairen Cao +1
Designing state encoders for reinforcement learning (RL) with multiple information sources -- such as sensor measurements, time-series signals, image observations, and textual inst…
cs.AI2025
Embodied World Models Emerge from Navigational Task in Open-Ended Environments
Li Jin, Liu Jia
Spatial reasoning in partially observable environments has often been approached through passive predictive models, yet theories of embodied cognition suggest that genuinely useful…
cs.LG2025
Reducing Action Space for Deep Reinforcement Learning via Causal Effect Estimation
Wenzhang Liu, Lianjun Jin, Lu Ren +2
Intelligent decision-making within large and redundant action spaces remains challenging in deep reinforcement learning. Considering similar but ineffective actions at each step ca…