Combining meta reinforcement learning with neural plasticity mechanisms for improved AI performance.
This research explores the potential of combining Meta Reinforcement Learning (MRL) with Spike-Timing-Dependent Plasticity (STDP) to enhance the performance and adaptability of AI agents in Atari game settings. Our methodology leverages MRL to swiftly adjust agent strategies across a range of games,...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0320777 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This research explores the potential of combining Meta Reinforcement Learning (MRL) with Spike-Timing-Dependent Plasticity (STDP) to enhance the performance and adaptability of AI agents in Atari game settings. Our methodology leverages MRL to swiftly adjust agent strategies across a range of games, while STDP fine-tunes synaptic weights based on neuronal spike timings, which in turn improves learning efficiency and decision-making under changing conditions. A series of experiments were conducted with standard Atari games to compare the hybrid MRL-STDP model against baseline models using traditional reinforcement learning techniques like Q-learning and Deep Q-Networks. Various performance metrics, including learning speed, adaptability, and cross-game generalization, were evaluated. The results show that the MRL-STDP approach significantly accelerates the agent's ability to reach competitive performance levels, with a 40% boost in learning efficiency and a 35% increase in adaptability over conventional models. |
|---|---|
| ISSN: | 1932-6203 |