Contributed Talk Sessions | Poster Sessions | All Posters | Search Papers

Poster Session B: Wednesday, August 13, 1:00 – 4:00 pm, de Brug & E‑Hall

Excitatory-Inhibitory Dynamics in Adaptive Decision-Making

Veronica Chelu¹, Doina Precup²; ¹McGill University, ²DeepMind

Presenter: Veronica Chelu

Neural circuits rely on excitatory–inhibitory (E/I) interactions to support adaptive learning and decision-making. Here, we investigate how these dynamics contribute to flexible behaviour across three modelling levels. First, using a simplified mean-field model of two-choice decision-making, we examine the computational role of selective excitation and inhibition in stabilizing or amplifying competition between alternative choices. Building on these insights, we embed a similar E/I mechanism into the preference function of a reinforcement learning (RL) agent, showing how inhibitory feedback modulates behavioural adaptation in dynamic tasks. Finally, we assess the scalability of these principles by training RL agents with E/I-constrained recurrent neural networks (RNNs) in changing environments. While a general E/I architecture allows broader forms of inhibitory influence, our results indicate it hinders learning in these settings. In contrast, a structured architecture enforcing locally-constrained inhibition preserves biological plausibility while maintaining robust performance. Together, these findings suggest that E/I dynamics may provide a feasible computational mechanism for flexible decision-making and continual learning.

Topic Area: Reward, Value & Social Decision Making

Extended Abstract: Full Text PDF