Russell Mendonca

reinforcement learning (3) visual affordance (2) policy search (2) world model (2) imitation learning (2) robotic manipulation (1) visual representation (1) robot learning (1) model-based reinforcement learning (1) off-policy learning (1) disentangled representation (1) unsupervised skill discovery (1) fast adaptation (1) meta-reinforcement learning (1) exploration strategy (1) goal-conditioned reinforcement learning (1) structured noise (1) auxiliary loss (1) manipulation skill (1) goal reaching (1)