Truncated Approximate Dynamic Programming with Task-Dependent Terminal Value.
Amir-massoud FarahmandDaniel Nikolaev NikovskiYuji IgarashiHiroki KonakaPublished in: AAAI (2016)
Keyphrases
- approximate dynamic programming
- linear program
- stochastic dynamic programming
- dynamic programming
- reinforcement learning
- step size
- control policy
- average cost
- factored mdps
- linear programming
- policy iteration
- evolutionary algorithm
- probability distribution
- state space
- markov decision processes
- influence diagrams
- image sequences
- learning algorithm