Harnessing Structures for Value-Based Planning and Reinforcement Learning.
Yuzhe YangGuo ZhangZhi XuDina KatabiPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- action selection
- partial observability
- reinforcement learning algorithms
- goal oriented
- partially observable
- multi agent
- markov decision processes
- macro actions
- domain independent
- planning problems
- function approximation
- collective intelligence
- reinforcement learning problems
- deterministic domains
- stochastic domains
- multi agent reinforcement learning
- markov decision problems
- temporal difference
- decision theoretic
- decision support