Tremendous progress has been made in reinforcement learning (RL) over the past decade.
Most of these advancements came through the continual development of new algorithms …

We consider infinite-horizon discounted Markov decision processes and study the
convergence rates of the natural policy gradient (NPG) and the Q-NPG methods with the log …

Abstract Black-Box Optimization (BBO) is increasingly vital for addressing complex real-
world optimization challenges, where traditional methods fall short due to their reliance on …

This manuscript gives a big-picture, up-to-date overview of the field of (deep) reinforcement
learning and sequential decision making, covering value-based RL, policy-gradient …

Modern policy optimization methods in reinforcement learning, such as TRPO and PPO, owe
their success to the use of parameterized policies. However, while theoretical guarantees …

The necessity for cooperation among intelligent machines has popularised cooperative multi-
agent reinforcement learning (MARL) in AI research. However, many research endeavours …

Abstract Learning With Opponent-Learning Awareness (LOLA)(Foerster et al.[2018a]) is a
multi-agent reinforcement learning algorithm that typically learns reciprocity-based …

Recent advancements in meta-learning have enabled the automatic discovery of novel
reinforcement learning algorithms parameterized by surrogate objective functions. To …

The necessity for cooperation among intelligent machines has popularised cooperative multi-
agent reinforcement learning (MARL) in the artificial intelligence (AI) research community …

Despite the success of cooperative multi-agent reinforcement learning algorithms, most of
them focus on a single team composition, which prevents them from being used in more …