Optimistic Temporal Difference Learning for 2048.
Hung GueiLung-Pin ChenI-Chen WuPublished in: CoRR (2021)
Keyphrases
- temporal difference learning
- function approximation
- fixed point
- evaluation function
- reinforcement learning
- temporal difference
- game playing
- reinforcement learning algorithms
- markov decision process
- approximate value iteration
- state space
- monte carlo
- function approximators
- dynamical systems
- markov decision processes
- model free