Angelos Filos

successor feature (2) epistemic uncertainty (2) model-based reinforcement learning (2) multi-task learning (1) state abstraction (1) imitation learning (1) function approximation (1) knowledge transfer (1) inverse reinforcement learning (1) value function (1) multi-agent learning (1) generalization error (1) distribution shift (1) policy improvement (1) value estimation (1) autonomous vehicle (1) zero-shot transfer (1) few-shot transfer (1) online adaptation (1) block mdp (1)