Experimental Results on Learning Stochastic Memoryless Policies for Partially Observable Markov Decision Processes.
John K. WilliamsSatinder P. SinghPublished in: NIPS (1998)
Keyphrases
- partially observable markov decision processes
- reinforcement learning
- predictive state representations
- learning algorithm
- stochastic domains
- partially observable
- model free reinforcement learning
- optimal policy
- decision makers
- decision problems
- multi agent
- dynamic programming
- dynamic environments
- dynamical systems
- finite state