On-policy concurrent reinforcement learning.
Bikramjit BanerjeeSandip SenJing PengPublished in: J. Exp. Theor. Artif. Intell. (2004)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- action selection
- hierarchical reinforcement learning
- function approximation
- reinforcement learning problems
- reinforcement learning algorithms
- state and action spaces
- function approximators
- semi markov decision process
- partially observable environments
- policy gradient
- state space
- markov decision processes
- markov decision problems
- control policies
- reward function
- policy iteration
- control policy
- model free
- partially observable
- actor critic
- action space
- average reward
- policy evaluation
- rl algorithms
- state action
- partially observable markov decision processes
- temporal difference
- continuous state spaces
- infinite horizon
- multi agent
- approximate dynamic programming
- decision problems
- model free reinforcement learning
- reinforcement learning methods
- temporal difference learning
- asymptotically optimal
- least squares
- inverse reinforcement learning
- average cost
- robotic control
- allocation policy
- machine learning
- finite state
- gradient method
- long run
- state dependent