HiT-MDP: Learning the SMDP option framework on MDPs with Hidden Temporal Embeddings.
Chang LiDongjin SongDacheng TaoPublished in: ICLR (2023)
Keyphrases
- markov decision processes
- reinforcement learning
- factored mdps
- markov decision problems
- markov decision process
- learning algorithm
- state space
- decision theoretic
- decision theoretic planning
- dynamic programming
- semi markov decision processes
- semi markov decision process
- partially observable
- hierarchical reinforcement learning
- state and action spaces
- optimal policy
- partially observable markov decision process
- linear program
- learning tasks
- linear programming
- policy iteration
- reward shaping