Quasi-Monte Carlo Initialization for Meta-Reinforcement Learning

Online Robust Reinforcement Learning Through Monte-Carlo Planning

A new robust variant of MCTS that mitigates dynamical model ambiguities to bridge the gap between simulation-based planning and real-world deployment and empirical evidence is provided that this method achieves robust performance in planning problems even under significant ambiguity in the underlying reward distributio...

Theoretical Aspects of Reinforcement Learning: A Special Issue of AMOP

This work states that there has been an upsurge of interest and development of RL theory and applications in the communities of stochastic control, stochastic analysis and unsupervised learning.

Reinforcement Learning as (Discrete) Potential Theory

This paper explores the potential-theoretic viewpoint for core reinforcement learning representations and algorithms under a fixed-policy assumption and may offer a path for improved sample efficiency and formal constraints that can be applied to RL.

Uncertainty-Weighted Optimisation for Model-Based Reinforcement Learning

In Model-Based Reinforcement Learning, Deep Neural Networks are trained to be world models to simulate interactions between agents and their environments. Model biases are inevitable in such world models due to their limited size and the stochastic nature of training datasets. Instead of striving for a perfect world mo...

Continuous Monte Carlo Search

Adaptive Mixing of Policies from Searching and Policies from Learning

Flexer is described, an architecture that, for each step, mixes the policy from a neural network and the policy from Monte Carlo tree search, the mixing factor favors the MCTS policy as the policy imitation error of the network and the environment models'variance increases.