Planning as Dynamics Relaxation: Hippocampal Recurrent Network Realizes Optimal Goal-Directed Navigation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
The Flow has not summarised this story yet — read it at arXiv AI.
arXiv:2603.15412v2 Announce Type: replace Abstract: The mammalian brain, most extensively studied in rodents and bats, solves an enormous variety of non-spatial cognitive tasks using neural circuitry...
arXiv:2606. 01868v1 Announce Type: new Abstract: Reinforcement Learning (RL) has long served as a model for goal-directed animal behavior in neuroscience.
arXiv:2609.38383v1 Announce Type: cross Abstract: Random exploration reveals how an environment can be traversed before a goal is specified. Can this experience support long-range planning without po...
The paper proposes a biologically plausible framework to approximate backpropagation through time (BPTT) for learning complex temporal dependencies in neuronal circuits. It derives a time‑continuous equivalent of BPTT using a prospective energy function and introduces a learning rule for backward weights that ensures fully local space‑time dynamics, correcting gain errors inherent in previous approximations. This approach unifies and extends prior local, phase‑free credit assignment methods, offering a rigorous basis for spatiotemporal deep learning in the brain and guiding the design of physical circuits that implement these computations.
The paper introduces ELiSe, a model that leverages cortical network scaffolds and dendritic compartments to learn complex non‑Markovian spatio‑temporal patterns using only local, always‑on, phase‑free synaptic plasticity. It demonstrates the model’s ability to acquire and replay intricate sequences, exemplified by a birdsong learning mock‑up, and shows robustness to external disturbances and flexibility in parameter settings.
Compact Bellman-Grounded Cognitive Maps (BCM) are introduced as a new method for cost-aware navigation that reuses a single learned map for different goals without per-goal retraining. BCM grounds the map in local edge costs using a self-supervised Bellman objective and a compact coordinate encoding, achieving near-optimal performance on weighted grids up to 1600 nodes with only a 5% mean gap to exact Dijkstra search. Its memory footprint grows sublinearly with graph size, outperforming connectivity-based spectral baselines and demonstrating scalability to complex environments.