Persistent Reinforcement Learning via Subgoal Curricula.
Archit SharmaAbhishek GuptaSergey LevineKarol HausmanChelsea FinnPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- goal oriented
- multi agent
- computer science
- markov decision processes
- model free
- evolutionary learning
- reinforcement learning algorithms
- partial order
- state space
- machine learning
- temporal difference
- website
- artificial intelligence
- learning algorithm
- genetic algorithm
- optimal policy
- expert systems
- case study
- optimal control
- control problems
- temporal difference learning
- real time