Joel Veness
59 works · 39,865 citations · h-index 17
Top works
- Human-level control through deep reinforcement learning
- Overcoming catastrophic forgetting in neural networks
- Investigating Contingency Awareness Using Atari 2600 Games
- The Arcade Learning Environment: An Evaluation Platform for General Agents
- Monte-Carlo Planning in Large POMDPs
- Bootstrapping from Game Tree Search
- Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents
- Sketch-Based Linear Value Function Approximation
- Bayesian Learning of Recursively Factored Environments
- Context Tree Switching
- A Monte-Carlo AIXI Approximation
- Skip Context Tree Switching
- The Forget-me-not Process
- An Approximation of the Universal Intelligence Measure
- An Approximation of the Universal Intelligence Measure
- Effective Use of Transposition Tables in Stochastic Game Tree Search
- Reinforcement Learning via AIXI Approximation
- Language Modeling Is Compression
- Meta-learning of Sequential Strategies
- Variance Reduction in Monte-Carlo Tree Search