Similar Items: What’s Next if Reward is Enough? Insights for AGI from Animal Reinforcement Learning
- The Archimedean trap: Why traditional reinforcement learning will probably not yield AGI
- Exploration and Exploitation: A Study on Sample Efficiency in Reinforcement Learning With Multifaceted Curiosity Rewards and Adaptive Experience Replay Utilisation in Sparse Reward Environments
- Integrating survival into reward functions for reinforcement learning in financial trading
- Learning and decision-making in artificial animals
- Extending Environments to Measure Self-reflection in Reinforcement Learning
- Feature Reinforcement Learning: Part II. Structured MDPs