A Policy-Guided Imitation Approach for Offline Reinforcement Learning.
Haoran XuLi JiangJianxiong LiXianyuan ZhanPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- action selection
- function approximation
- partially observable
- control policies
- state space
- reinforcement learning algorithms
- reinforcement learning problems
- function approximators
- actor critic
- policy iteration
- control policy
- state action
- markov decision problems
- approximate dynamic programming
- policy evaluation
- partially observable markov decision processes
- infinite horizon
- reward function
- action space
- partially observable environments
- markov decision processes
- continuous state spaces
- state and action spaces
- policy gradient
- machine learning
- temporal difference
- dynamic programming
- model free reinforcement learning
- continuous state
- rl algorithms
- model free
- control problems
- real time
- finite state
- reinforcement learning methods
- multi agent
- average reward
- optimal control
- learning problems
- imitation learning
- learning process
- learning algorithm
- partially observable domains
- long run
- decision problems
- transfer learning
- robotic control
- learning classifier systems