Reinforcement Learning
Future-Dependent Value-Based Off-Policy Evaluation in POMDPs
Existing methods such as sequential importance sampling estimators suffer from the curse of horizon in POMDPs.
Physics-Driven ML-Based Modelling for Correcting Inverse Estimation
When deploying machine learning estimators in science and engineering (SAE) domains, it is critical to avoid failed estimations that can have disastrous consequences, e.g., in aero engine design.
Distributional Pareto-Optimal Multi-Objective Reinforcement Learning
Consequently, MORL's primary aim is to learn a variety of
Replicable Reinforcement Learning
The replicability crisis in the social, behavioral, and data sciences has led to the formulation of algorithm frameworks for replicability -- i.e., a requirement that an algorithm produce identical outputs (with high probability) when run on two
Coherent Soft Imitation Learning Joe Watson Sandy H. Huang Nicolas Heess
Imitation learning methods seek to learn from an expert either through behavioral cloning (BC) for the policy or inverse reinforcement learning (IRL) for the reward. Such methods enable agents to learn complex tasks from humans that are difficult to capture with hand-designed reward functions.
Policy Optimization for Continuous Reinforcement Learning
Through numerical experiments, we demonstrate the effectiveness and advantages of our approach.