Paper
Publication
On the Role of Neural Collapse in Transfer Learning
Paper
Publication
The Effectiveness of Memory Replay in Large Scale Continual Learning
Paper
Publication
Importance Weighted Policy Learning and Adaption
Paper
Publication
Data-efficient Hindsight Off-policy Option Learning
Paper
Publication
CoMic: Complementary Task Learning & Mimicry for Reusable Skills
Paper
Publication
Rapid Task-Solving in Novel Environments
Paper
Publication
Principal Neighbourhood Aggregation for Graph Nets
Paper
Publication
XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization
Paper
Publication
Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning
Paper
Publication
A distributional code for value in dopamine-based reinforcement learning
Paper
Publication
The Option Keyboard Combining Skills in Reinforcement Learning
Paper
Publication
Deep Neuroethology of a Virtual Rodent
Paper
Publication
V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control
Paper
Publication
Regularized Hierarchical Policies for Compositional Transfer in Robotics
Paper
Publication
COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration
Paper
Publication
Functional Regularisation for Continual Learning
Paper
Publication
Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement
Paper
Publication
Universal Successor Features Approximators
Paper
Publication
Information Asymmetry in KL-Regularized RL
Paper
Publication
Sample Efficient Adaptive Text-to-Speech
Paper
Publication
Syntactic Scaffolds for Semantic Structures
Paper
Publication
Mix&Match - Agent Curricula for Reinforcement Learning
Paper
Publication
Progress & Compress: A scalable framework for continual learning
Paper
Publication
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Paper
Publication
Multi-Task Self-Supervised Visual Learning