Electrified vehicles provide an effective solution to address the unfavorable impacts of fossil
fuel use in the transportation sector. Energy management strategy (EMS) is the core …

Policy gradient methods are among the most effective methods in challenging reinforcement
learning problems with large state and/or action spaces. However, little is known about even …

Policy gradient (PG) methods are among the most effective methods in challenging
reinforcement learning problems with large state and/or action spaces. However, little is …

Learning from demonstration, or imitation learning, is the process of learning to act in an
environment from examples provided by a teacher. Inverse reinforcement learning (IRL) is a …

While policy-based reinforcement learning (RL) achieves tremendous successes in practice,
it is significantly less understood in theory, especially compared with value-based RL. In …

Many recent successful (deep) reinforcement learning algorithms make use of
regularization, generally based on entropy or Kullback-Leibler divergence. We propose a …

We establish a new connection between value and policy based reinforcement learning
(RL) based on a relationship between softmax temporal value consistency and policy …

Proximal policy optimization and trust region policy optimization (PPO and TRPO) with actor
and critic parametrized by neural networks achieve significant empirical success in deep …

Model-free reinforcement learning algorithms, such as Q-learning, perform poorly in the
early stages of learning in noisy environments, because much effort is spent unlearning …

We propose a general framework for entropy-regularized average-reward reinforcement
learning in Markov decision processes (MDPs). Our approach is based on extending the …