Prediction And Control With Temporal Segment Models

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymishra2017prediction

Related papers

• Generative Temporal Difference Learning For Infinite-horizon Prediction (2020)0.00
• Learning When To Act: Interval-aware Reinforcement Learning With Predictive Temporal Structure (2026)0.00
• Model-based Reinforcement Learning For Control Under Time-varying Dynamics (2026)0.00
• Prediction And Control In Continual Reinforcement Learning (2023)0.00
• An Efficient, Expressive And Local Minima-free Method For Learning Controlled Dynamical Systems (2017)2.26
• Temporal Difference Models: Model-free Deep RL For Model-based Control (2018)0.00
• Dream To Explore: Adaptive Simulations For Autonomous Systems (2021)0.00
• Sample Complexity Of Estimating The Policy Gradient For Nearly Deterministic Dynamical Systems (2019)0.00