時間セグメントモデルによる予測と制御
Prediction and Control with Temporal Segment Models
状態と行動の時間セグメント上の深層生成モデルで複雑な非線形システムのダイナミクスを学習し、長期的な予測とモデルベース方策最適化を実現した。
著者: Nikhil Mishra, Pieter Abbeel, Igor Mordatch
分類: cs.LG, cs.AI, cs.RO, stat.ML
原文アブストラクト
We introduce a method for learning the dynamics of complex nonlinear systems based on deep generative models over temporal segments of states and actions. Unlike dynamics models that operate over individual discrete timesteps, we learn the distribution over future state trajectories conditioned on past state, past action, and planned future action trajectories, as well as a latent prior over action trajectories. Our approach is based on convolutional autoregressive models and variational autoencoders. It makes stable and accurate predictions over long horizons for complex, stochastic systems, effectively expressing uncertainty and modeling the effects of collisions, sensory noise, and action delays. The learned dynamics model and action prior can be used for end-to-end, fully differentiable trajectory optimization and model-based policy optimization, which we use to evaluate the performance and sample-efficiency of our method.
