Dream To Explore: Adaptive Simulations For Autonomous Systems

Abstract

One's ability to learn a generative model of the world without supervision depends on the extent to which one can construct abstract knowledge representations that generalize across experiences. To this end, capturing an accurate statistical structure from observational data provides useful inductive biases that can be transferred to novel environments. Here, we tackle the problem of learning to control dynamical systems by applying Bayesian nonparametric methods, which is applied to solve visual servoing tasks. This is accomplished by first learning a state space representation, then inferring environmental dynamics and improving the policies through imagined future trajectories. Bayesian nonparametric models provide automatic model adaptation, which not only combats underfitting and overfitting, but also allows the model's unbounded dimension to be both flexible and computationally tractable. By employing Gaussian processes to discover latent world dynamics, we mitigate common data e

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysheikhbahaee2021dream

Related papers

• Dream To Control: Learning Behaviors By Latent Imagination (2019)0.00
• Discovering Latent States For Model Learning: Applying Sensorimotor Contingencies Theory And Predictive Processing To Model Context (2016)0.00
• Learning Robust And Adaptive Real-world Continuous Control Using Simulation And Transfer Learning (2018)0.00
• Metacontrol For Adaptive Imagination-based Optimization (2017)0.00
• Reasoning About Unforeseen Possibilities During Policy Learning (2018)0.00
• Curiosity-driven Exploration Via Latent Bayesian Surprise (2021)0.00
• Optimal Exploration For Model-based RL In Nonlinear Systems (2023)0.00
• Optimistic Active Exploration Of Dynamical Systems (2023)0.00