Abstract | ||
---|---|---|
We propose an effective way to create interpretable control agents, by re-purposing the function of a biological neural circuit model, to govern simulated and real world reinforcement learning (RL) test-beds. We model the tap-withdrawal (TW) neural circuit of the nematode, C. elegans, a circuit responsible for the worm's reflexive response to external mechanical touch stimulations, and learn its synaptic and neuronal parameters as a policy for controlling basic RL tasks. We also autonomously park a real rover robot on a pre-defined trajectory, by deploying such neuronal circuit policies learned in a simulated environment. For reconfiguration of the purpose of the TW neural circuit, we adopt a search-based RL algorithm. We show that our neuronal policies perform as good as deep neural network policies with the advantage of realizing interpretable dynamics at the cell level. |
Year | Venue | DocType |
---|---|---|
2018 | CoRR | Journal |
Volume | Citations | PageRank |
abs/1803.08554 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mathias Lechner | 1 | 0 | 1.69 |
Ramin M. Hasani | 2 | 14 | 10.88 |
Radu Grosu | 3 | 1011 | 97.48 |