Contextual Conservative Q-Learning for Offline Reinforcement Learning.
Ke JiangJiayu YaoXiaoyang TanPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- state space
- model free
- contextual information
- state action space
- optimal policy
- markov decision processes
- action selection
- context sensitive
- learning algorithm
- multi agent reinforcement learning
- temporal difference
- continuous state and action spaces
- stochastic approximation
- control problems
- reinforcement learning methods
- supervised learning
- multi agent
- machine learning
- policy search
- state action
- learning problems
- dynamic programming
- real time
- temporal difference learning
- transfer learning
- relational reinforcement learning
- sequential decision problems
- policy iteration
- learning agent
- function approximators
- learning capabilities
- learning tasks
- td learning
- eligibility traces
- temporal difference methods
- learning process