Model-based Offline Reinforcement Learning with Count-based Conservatism.
Byeongchan KimMin Hwan OhPublished in: ICML (2023)
Keyphrases
- reinforcement learning
- model free
- function approximation
- state space
- real time
- machine learning
- markov decision processes
- optimal control
- optimal policy
- policy search
- learning problems
- case study
- multi agent systems
- knowledge base
- learning algorithm
- temporal difference
- control policy
- multi agent reinforcement learning
- data mining