Ask a Question

Prefer a chat interface with context about you and your work?

Reinforcement Learning with Non-Markovian Rewards

Reinforcement Learning with Non-Markovian Rewards

The standard RL world model is that of a Markov Decision Process (MDP). A basic premise of MDPs is that the rewards depend on the last state and action only. Yet, many real-world rewards are non-Markovian. For example, a reward for bringing coffee only if requested earlier and not yet …