Daniel J. Mankowitz
52 works · 4,063 citations · h-index 19
Top works
- Competition-level code generation with AlphaCode
- Gemini: A Family of Highly Capable Multimodal Models
- Challenges of real-world reinforcement learning: definitions, benchmarks and analysis
- A Deep Hierarchical Approach to Lifelong Learning in Minecraft
- Reward Constrained Policy Optimization
- Challenges of Real-World Reinforcement Learning
- Faster sorting algorithms discovered using deep reinforcement learning
- Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning
- Adaptive Skills, Adaptive Partitions (ASAP)
- An empirical investigation of the challenges of real-world reinforcement learning
- Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement
- Robust Reinforcement Learning for Continuous Control with Model Misspecification
- Unicorn: Continual Learning with a Universal, Off-policy Agent
- Time-regularized interrupting options
- Learning How Not to Act in Text-based Games
- Learning Robust Options
- Time-Regularized Interrupting Options (TRIO)
- Iterative Hierarchical Optimization for Misspecified Problems (IHOMP)
- RL Unplugged: Benchmarks for Offline Reinforcement Learning.
- Soft-Robust Actor-Critic Policy-Gradient