Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models
arXiv:1808.04768
Abstract
We introduce a method which enables a recurrent dynamics model to be temporally abstract. Our approach, which we call Adaptive Skip Intervals (ASI), is based on the observation that in many sequential prediction tasks, the exact time at which events occur is irrelevant to the underlying objective. Moreover, in many situations, there exist prediction intervals which result in particularly easy-to-predict transitions. We show that there are prediction tasks for which we gain both computational efficiency and prediction accuracy by allowing the model to make predictions at a sampling rate which it can choose itself.
References in corpus (15)
- Adam: A Method for Stochastic Optimization
- Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
- Action-Conditional Video Prediction using Deep Networks in Atari Games
- Imagination-Augmented Agents for Deep Reinforcement Learning
- Temporal Difference Models: Model-Free Deep RL for Model-Based Control
- The Predictron: End-To-End Learning and Planning
- On Causal and Anticausal Learning
- Recurrent Environment Simulators
- Self-Supervised Visual Planning with Temporal Skip Connections
- Learning and Transfer of Modulated Locomotor Controllers
- Learning Independent Causal Mechanisms
- Learning and Querying Fast Generative Models for Reinforcement Learning
- Value Prediction Network
- Time-Agnostic Prediction: Predicting Predictable Video Frames
- Sparse Attentive Backtracking: Long-Range Credit Assignment in Recurrent Networks
Cited by in corpus (4)
- Accelerating Deep Reinforcement Learning strategies of Flow Control through a multi-environment approach
- Robust active flow control over a range of Reynolds numbers using an artificial neural network trained through deep reinforcement learning
- Temporal Difference Variational Auto-Encoder
- Variational Predictive Routing with Nested Subjective Timescales