Bart Dhoedt

reinforcement learning (2) self-supervised learning (1) multimodal learning (1) policy learning (1) task generalization (1) model predictive control (1) model-based reinforcement learning (1) belief updating (1) free energy (1) intrinsic motivation (1) generative model (1) foundation model (1) latent space (1) world model (1) embodied agent (1) unsupervised reinforcement learning (1) task adaptation (1) latent space exploration (1) active inference (1) curiosity-driven exploration (1)