Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning.
Yuhui WangQingyuan WuWeida LiDylan R. AshleyFrancesco FaccioChao HuangJürgen SchmidhuberPublished in: CoRR (2024)
Keyphrases
- long term
- heuristic search
- short term
- belief space
- state space
- markov decision processes
- complex networks
- network structure
- learning algorithm
- social networks
- planning problems
- stochastic domains
- infinite horizon
- optimal policy
- dynamic programming
- decision theoretic
- wireless sensor networks
- belief state
- power law
- ai planning
- partially observable markov decision processes
- machine learning
- data sets