Sequential Triggers for Watermarking of Deep Reinforcement Learning Policies.
Vahid BehzadanWilliam H. HsuPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- control policies
- markov decision process
- markov decision processes
- function approximation
- reward function
- reinforcement learning agents
- hierarchical reinforcement learning
- state space
- digital images
- control policy
- partially observable markov decision processes
- reinforcement learning algorithms
- policy gradient methods
- markov decision problems
- dynamic programming
- continuous state
- multi agent reinforcement learning
- model free
- deep learning
- watermarking algorithm
- multiagent reinforcement learning
- finite state
- watermarking scheme
- multi agent
- image processing operations
- fragile watermarking
- image watermarking
- fitted q iteration
- robust image watermarking
- watermarking method
- neural network
- image authentication
- average reward
- digital watermarking
- learning agent
- active databases
- temporal difference
- decision problems
- multiagent systems
- mobile robot
- hidden markov models
- learning algorithm
- machine learning