P3O: Policy-on Policy-off Policy Optimization.
Rasool FakoorPratik ChaudhariAlexander J. SmolaPublished in: CoRR (2019)
Keyphrases
- optimal policy
- global optimization
- neural network
- policy making
- access control policies
- action selection
- optimization problems
- cost function
- image sequences
- optimization algorithm
- case study
- decision making
- conflict resolution
- information systems
- machine learning
- asymptotically optimal
- markov decision process
- real time