It is quite challenging to ensure the safety of reinforcement learning (RL) agents in an
unknown and stochastic environment under hard constraints that require the system state …

We consider model-free reinforcement learning (RL) in non-stationary Markov decision
processes. Both the reward functions and the state transition functions are allowed to vary …

We study the problem of learning a mixture of multiple linear dynamical systems (LDSs) from
unlabeled short sample trajectories, each generated by one of the LDS models. Despite the …

Transformer has achieved great successes in learning vision and language representation,
which is general across various downstream tasks. In visual control, learning transferable …

Reinforcement learning (RL) plays an essential role in the field of artificial intelligence but
suffers from data inefficiency and model-shift issues. One possible solution to deal with such …

Transfer reinforcement learning (RL) has recently received increasing attention to make RL
agents have better learning performance in target Markov decision problems (MDPs) by …

Abstract The Configurable Markov Decision Process framework includes two entities: a
Reinforcement Learning agent and a configurator that can modify some environmental …

Reinforcement Learning (RL) is crucial for data-driven decisionmaking but suffers from
sample inefficiency. This poses a risk to system safety and can be costly in real-world …

We consider model-free reinforcement learning (RL) in non-stationary Markov decision
processes. Both the reward functions and the state transition functions are allowed to vary …

Transferring knowledge among various environments is important for efficiently learning
multiple tasks online. Most existing methods directly use the previously learned models or …