Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks.
Amin RakhshaGoran RadanovicRati DevidzeXiaojin ZhuAdish SinglaPublished in: J. Mach. Learn. Res. (2021)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- agent learns
- learning process
- action selection
- markov decision process
- agent receives
- e learning
- function approximation
- countermeasures
- control policy
- mobile robot
- real time
- machine learning
- policy evaluation
- action space
- higher education
- complex environments
- policy iteration
- real robot
- average reward
- control policies
- continuous state
- autonomous learning
- educational technology
- reinforcement learning problems
- optimal control
- high school