Dual Generator Offline Reinforcement Learning.
Quan VuongAviral KumarSergey LevineYevgen ChebotarPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- state space
- function approximation
- real time
- multi agent
- machine learning
- transfer learning
- temporal difference
- relational reinforcement learning
- model free
- control problems
- reinforcement learning algorithms
- action selection
- policy search
- markov decision processes
- optimal policy
- artificial intelligence
- robotic control
- direct policy search
- multi agent reinforcement learning
- optimal control
- dynamic programming
- information retrieval
- data sets