• Publications
  • Influence
Continuous control with deep reinforcement learning
TLDR
This work presents an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces, and demonstrates that for many of the tasks the algorithm can learn policies end-to-end: directly from raw pixel inputs.
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
TLDR
This work proposes an alternative to Bayesian NNs that is simple to implement, readily parallelizable, requires very little hyperparameter tuning, and yields high quality predictive uncertainty estimates.
Deep Exploration via Bootstrapped DQN
Efficient exploration in complex environments remains a major challenge for reinforcement learning. We propose bootstrapped DQN, a simple algorithm that explores in a computationally and
Highly accurate protein structure prediction with AlphaFold
TLDR
This work validated an entirely redesigned version of the neural network-based model, AlphaFold, in the challenging 14th Critical Assessment of protein Structure Prediction (CASP14)15, demonstrating accuracy competitive with experiment in a majority of cases and greatly outperforming other methods.
PathNet: Evolution Channels Gradient Descent in Super Neural Networks
TLDR
Successful transfer learning is demonstrated; fixing the parameters along a path learned on task A and re-evolving a new population of paths for task B, allows task B to be learned faster than it could be learned from scratch or after fine-tuning.
DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
TLDR
A new multi-stage RL agent, DARLA (DisentAngled Representation Learning Agent), which learns to see before learning to act, which significantly outperforms conventional baselines in zero-shot domain adaptation scenarios.
Vector-based navigation using grid-like representations in artificial agents
TLDR
These findings show that emergent grid-like representations furnish agents with a Euclidean spatial metric and associated vector operations, providing a foundation for proficient navigation, and support neuroscientific theories that see grid cells as critical for vector-based navigation.
Never Give Up: Learning Directed Exploration Strategies
TLDR
This work constructs an episodic memory-based intrinsic reward using k-nearest neighbors over the agent's recent experience to train the directed exploratory policies, thereby encouraging the agent to repeatedly revisit all states in its environment.
Memory-based Parameter Adaptation
TLDR
Memory-based Parameter Adaptation alleviates several shortcomings of neural networks, such as catastrophic forgetting, fast, stable acquisition of new knowledge, learning with an imbalanced class labels, and fast learning during evaluation.
Highly accurate protein structure prediction for the human proteome
TLDR
This work dramatically expands structural coverage by applying the state-of-the-art machine learning method, AlphaFold, at scale to almost the entire human proteome, covering 58% of residues with a confident prediction, of which a subset have very high confidence.
...
1
2
3
...