Poster
Probabilistic Planning with Sequential Monte Carlo methods
Alexandre Piche · Valentin Thomas · Cyril Ibrahim · Yoshua Bengio · Christopher Pal
Keywords: [ sequential monte carlo ] [ control as inference ] [ probabilistic planning ] [ model based reinforcement learning ]
In this work, we propose a novel formulation of planning which views it as a probabilistic inference problem over future optimal trajectories. This enables us to use sampling methods, and thus, tackle planning in continuous domains using a fixed computational budget. We design a new algorithm, Sequential Monte Carlo Planning, by leveraging classical methods in Sequential Monte Carlo and Bayesian smoothing in the context of control as inference. Furthermore, we show that Sequential Monte Carlo Planning can capture multimodal policies and can quickly learn continuous control tasks.