Reptile: A scalable meta-learning algorithm
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Some considerations on learning to explore via meta-reinforcement learning
Multi-Goal Reinforcement Learning: Challenging robotics environments and request for rese…
Ingredients for robotics research
Interpretable machine learning through teaching
Discovering types for entity disambiguation
Requests for Research 2.0
Learning sparse neural networks through L₀ regularization
Interpretable and pedagogical examples
Learning a hierarchy
Generalizing from simulation
Sim-to-real transfer of robotic control with dynamics randomization
Asymmetric actor critic for image-based robot learning
Domain randomization and generative models for robotic grasping
Meta-learning for wrestling
Competitive self-play
Nonlinear computation in deep linear networks
Learning to model other minds
Learning with opponent-learning awareness
More on Dota 2
Dota 2
Better exploration with parameter noise
Hindsight Experience Replay
Teacher–student curriculum learning
Learning from human preferences
Learning to cooperate, compete, and communicate
UCB exploration via Q-ensembles
Robots that learn
Equivalence between policy gradients and soft Q-learning
Stochastic Neural Networks for hierarchical reinforcement learning