Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning.
Tenglong LiuYang LiYixing LanHao GaoWei PanXin XuPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- actor critic
- function approximation
- action selection
- markov decision process
- partially observable environments
- function approximators
- state space
- reinforcement learning problems
- reinforcement learning algorithms
- learning capabilities
- optimal control
- adaptive control
- markov decision processes
- control policy
- markov decision problems
- state action
- policy gradient
- policy evaluation
- action space
- partially observable
- state and action spaces
- machine learning
- inverse reinforcement learning
- partially observable domains
- continuous state
- control problems
- reward function
- temporal difference
- prior information
- cost function
- multi agent