Tim Harley
16 works · 4,151 citations · h-index 11
Top works
- Asynchronous Methods for Deep Reinforcement Learning
- Hybrid computing using a neural network with dynamic external memory
- IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
- The Predictron: End-To-End Learning and Planning
- Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes
- Unsupervised Predictive Memory in a Goal-Directed Agent
- A Generalized Framework for Population Based Training
- Multiplicative Interactions and Where to Find Them
- Imitating Interactive Intelligence
- Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text
- Scaling Instructable Agents Across Many Simulated Worlds
- Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning
- Robust Instruction-Following in a Situated Agent via Transfer-Learning from Text
- Population Based Training as a Service
- SIMA 2: A Generalist Embodied Agent for Virtual Worlds
- 集団ベース訓練のための一般化フレームワーク【JST・京大機械翻訳】