2 papers
cs.LG2026
Infant Spontaneous Movement Noise Improves Exploration in Deep RL
Francisco M. López, Markus R. Ernst, Francisco Cruz +2
Exploration in deep reinforcement learning (RL) is commonly implemented as temporally uncorrelated white noise. However, recent works show that temporally correlated colored noise…
cs.LG2026
ARROW: Augmented Replay for RObust World models
Abdulaziz Alyahya, Abdallah Al Siyabi, Markus R. Ernst +3
Continual reinforcement learning challenges agents to acquire new skills while retaining previously learned ones with the goal of improving performance in both past and future task…