Reachability Constrained Reinforcement Learning.
Dongjie YuHaitong MaSheng-bo LiJianyu ChenPublished in: ICML (2022)
Keyphrases
- reinforcement learning
- state space
- function approximation
- model free
- optimal policy
- reinforcement learning algorithms
- control problems
- action selection
- temporal difference
- machine learning
- multi agent reinforcement learning
- markov decision processes
- transitive closure
- optimal control
- markov decision process
- constrained problems
- real time
- policy search
- active exploration