Nested Policy Reinforcement Learning.
Aishwarya MandyamAndrew JonesKrzysztof LaudanskiBarbara EngelhardtPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- reinforcement learning problems
- control policies
- action selection
- function approximators
- function approximation
- control policy
- partially observable
- partially observable environments
- policy iteration
- reinforcement learning algorithms
- reward function
- policy gradient
- markov decision processes
- markov decision problems
- state and action spaces
- actor critic
- state space
- policy evaluation
- partially observable markov decision processes
- dynamic programming
- model free
- approximate dynamic programming
- continuous state
- average reward
- state action
- rl algorithms
- decision problems
- partially observable domains
- monte carlo search
- state dependent
- action space
- temporal difference
- machine learning
- agent learns
- model free reinforcement learning
- evaluation function
- eligibility traces
- control problems
- asymptotically optimal
- policy making
- learning process
- allocation policy
- partially observable markov decision process
- robotic control
- average cost
- approximate policy iteration
- monte carlo
- policy makers