Diana Borsa

Applications (1)

reinforcement learning (4) transfer learning (3) successor feature (2) value iteration (2) policy improvement (2) model-based reinforcement learning (2) deep reinforcement learning (2) reward function (1) state representation (1) policy gradient (1) bellman equation (1) importance sampling (1) policy evaluation (1) hierarchical reinforcement learning (1) off-policy learning (1) temporal-difference learning (1) epistemic uncertainty (1) value estimation (1) conditional value-at-risk (1) temporal difference learning (1)