Login / Signup
Learning Time-Invariant Reward Functions through Model-Based Inverse Reinforcement Learning.
Todor Davchev
Sarah Bechtle
Subramanian Ramamoorthy
Franziska Meier
Published in:
CoRR (2021)
Keyphrases
</>
inverse reinforcement learning
reward function
partially observable environments
reinforcement learning
preference elicitation
learning algorithm
transition probabilities
temporal difference