On the link between conscious function and general intelligence in humans and machines
Access consciousness and it’s relation to general intelligence
Access consciousness and it’s relation to general intelligence
Continual learning with a universal, off-policy agent.
Learned dynamics model with a GAN for image generation and MCTS for planning.
Unsupervised learning of image encoding, dynamics and reward models.
Unsupervised training of a memory that is used for prediction of state and reward.
Unsupervised learning of image encoding and dynamics model.
Pretraining Deep Actor-Critic Reinforcement Learning Algorithms With Expert Demonstrations.
Tensorizing LSTMs to make them wider and deeper without adding parameters and with minimal extra compute costs.
AlphaGo Zero, all RL self-play.
Pre-train using supervised learning on human provided demonstations.
A long review of the use of DL in robotics
A long review of the use of DL in robotics
Notes on using Eligibility Traces with neural networks
A single ML model used for very different tasks.
Relationships between objects.
Five questions to ask about your deep learning project.
Increase speed of a Reinforcement Learning system with auxiliary task.
Overview (with references) of attention and several types of augmentation for RNNs.
In-progress second edition of an RL textbook.
Improved Q-value estimation by reducing overestimates of Deep Q-networks.
One of the first deep reinforcement learning papers.
Off-Policy AC with linear state features. Includes elegibility traces.
Using RL value functions to encode semantic knowledge, specifically by a robot.