Abstract
Immediate rewards are usually very sparse in the real world, which brings a great challenge to plain learning methods. Inspired by the fact that emotional reactions are incorporated into the computation of subjective value during decision-making in humans, an emotion-motivated decision-making framework is proposed in this article. Specifically, we first build a brain-inspired computational model of amygdala-hippocampus interaction to generate emotional reactions. The intrinsic emotion derives from the external reward and episodic memory and represents three psychological states: 1) valence; 2) novelty; and 3) motivational relevance. Then, a model-based (MB) decision-making approach with emotional intrinsic rewards is proposed to solve the continuous control problem of mobile robots. This method can execute online MB control with the constraint of the model-free policy and global value function, which is conducive to getting a better solution with a faster policy search. The simulation results demonstrate that the proposed approach has higher learning efficiency and maintains a higher level of exploration, especially, in some very sparse-reward environments.
Original language | English |
---|---|
Article number | 8947977 |
Pages (from-to) | 31-44 |
Number of pages | 14 |
Journal | IEEE Transactions on Cognitive and Developmental Systems |
Volume | 13 |
Issue number | 1 |
DOIs | |
Publication status | Published - Mar 2021 |
Externally published | Yes |
Keywords
- Brain-inspired computing
- decision making
- emotion-memory interactions
- emotion-motivated learning
- reinforcement learning