Risto Vuorio

meta-reinforcement learning (2) few-shot learning (2) representation learning (1) reinforcement learning (1) sample efficiency (1) policy gradient (1) curriculum learning (1) self-supervised learning (1) gradient descent (1) state representation (1) gradient updates (1) fast adaptation (1) task distribution (1) general value function (1) policy generalization (1) auxiliary task (1) recurrent network (1) temporal credit assignment (1) multi-task rl (1) pairwise weighting (1)