Most reinforcement learning methods are based upon the key assumption that the transition
dynamics and reward functions are fixed, that is, the underlying Markov decision process is …

We study the problem of robust reinforcement learning under adversarial corruption on both
rewards and transitions. Our attack model assumes an\textit {adaptive} adversary who can …

This paper introduces an adaptive model-free deep reinforcement approach that can
recognize and adapt to the diurnal patterns in the ride-sharing environment with car-pooling …

Optimal decision-making presents a significant challenge for autonomous systems operating
in uncertain, stochastic and time-varying environments. Environmental variability over time …

The problem of continual learning in the domain of reinforcement learning, often called non-
stationary reinforcement learning, has been identified as an important challenge to the …

This paper examines the challenges associated with achieving life-long superalignment in
AI systems, particularly large language models (LLMs). Superalignment is a theoretical …

The problem of continual learning in the domain of reinforcement learning, often called non-
stationary reinforcement learning, has been identified as an important challenge to the …

While reinforcement learning (RL) algorithms have generated impressive strategies for a
wide range of tasks, the performance improvements in continuous-domain, real-world …

The development of Policy Iteration (PI) has inspired many recent algorithms for
Reinforcement Learning (RL), including several policy gradient methods that gained both …

This work studies a multi-agent Markov decision process (MDP) that can undergo agent
dropout and the computation of policies for the post-dropout system based on control and …