A Reinforcement Learning Algorithm in Partially Observable Environments Using Short-Term Memory.
Nobuo SuematsuAkira HayashiPublished in: NIPS (1998)
Keyphrases
- partially observable environments
- short term memory
- reinforcement learning algorithms
- reinforcement learning
- long term memory
- information processing
- state space
- markov decision processes
- model free
- computational model
- working memory
- computational modeling
- temporal difference
- learning algorithm
- function approximation
- reward function
- white matter
- inverse reinforcement learning
- cognitive architecture
- partially observable
- short term
- optimal policy
- data mining
- focus of attention
- long term
- cooperative games
- state variables
- human brain
- computational models
- search algorithm