StARformer: Transformer with State-Action-Reward Representations.
Jinghuan ShangMichael S. RyooPublished in: CoRR (2021)
Keyphrases
- state action
- reinforcement learning
- average reward
- evaluation function
- stochastic games
- action space
- markov decision process
- reward function
- state transitions
- function approximators
- belief state
- policy gradient
- markov decision processes
- long run
- fuzzy logic
- state space
- optimal policy
- random walk
- multi agent
- machine learning
- neural network
- least squares
- dynamic programming