Reinforcement Learning (RL) has achieved tremendous success in many complex decision-
making tasks. However, safety concerns are raised during deploying RL in real-world …

Abstract Safe Reinforcement Learning can be defined as the process of learning policies
that maximize the expectation of the return in problems in which it is important to ensure …

In many real-world reinforcement learning (RL) problems, besides optimizing the main
objective function, an agent must concurrently avoid violating a number of constraints. In …

Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to
maximize the accumulated reward, it often learns to exploit loopholes and misspecifications …

In many sequential decision-making problems one is interested in minimizing an expected
cumulative cost while taking into account risk, ie, increased awareness of events of small …

Autonomous agents must often deal with conflicting requirements, such as completing tasks
using the least amount of time/energy, learning multiple tasks, or dealing with multiple …

We propose RUDDER, a novel reinforcement learning approach for delayed rewards in
finite Markov decision processes (MDPs). In MDPs the Q-values are equal to the expected …

In many sequential decision-making problems we may want to manage risk by minimizing
some measure of variability in costs in addition to minimizing a standard criterion …

In many sequential decision-making problems we may want to manage risk by minimizing
some measure of variability in rewards in addition to maximizing a standard criterion …

Text-based interactive recommendation provides richer user preferences and has
demonstrated advantages over traditional interactive recommender systems. However …