Pacing Outside the Box: RNNs Learn to Plan in Sokoban
Pacing Outside the Box: RNNs Learn to Plan in Sokoban
far.ai Pacing Outside the Box: RNNs Learn to Plan in Sokoban | FAR AI
Giving RNNs extra thinking time at the start boosts their planning skills in Sokoban. We explore how this planning ability develops during reinforcement learning. Intriguingly, we find that on harder levels the agent paces around to get enough computation to find a solution.
0
comments