Introduces statistically efficient estimators for Renyi-α, Tsallis-α, reverse and forward KL divergences with REINFORCE and score-matching control variates for faster GFlowNet training.
Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
We present an algorithm for model-based reinforcement learning that combines Bayesian neural networks (BNNs) with random roll-outs and stochastic optimization for policy learning. The BNNs are trained by minimizing $\alpha$-divergences, allowing us to capture complicated statistical patterns in the transition dynamics, e.g. multi-modality and heteroskedasticity, which are usually missed by other common modeling approaches. We illustrate the performance of our method by solving a challenging benchmark where model-based approaches usually fail and by obtaining promising results in a real-world scenario for controlling a gas turbine.
fields
cs.LG 3verdicts
UNVERDICTED 3representative citing papers
Introduces a framework that learns an uncertainty-aware dynamics model and optimizes the policy via automatic differentiation through the model, reporting competitive asymptotic performance with significantly lower sample complexity than baselines on continuous control benchmarks.
Augmenting model-based RL agents with calibrated predictive uncertainties improves planning, sample efficiency, and exploration on continuous control tasks.
citing papers explorer
-
On Divergence Measures for Training GFlowNets
Introduces statistically efficient estimators for Renyi-α, Tsallis-α, reverse and forward KL divergences with REINFORCE and score-matching control variates for faster GFlowNet training.
-
Uncertainty-aware Model-based Policy Optimization
Introduces a framework that learns an uncertainty-aware dynamics model and optimizes the policy via automatic differentiation through the model, reporting competitive asymptotic performance with significantly lower sample complexity than baselines on continuous control benchmarks.
-
Calibrated Model-Based Deep Reinforcement Learning
Augmenting model-based RL agents with calibrated predictive uncertainties improves planning, sample efficiency, and exploration on continuous control tasks.