DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning.
Jinxin LiuHongyin ZhangDonglin WangPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- state space
- reward function
- markov decision processes
- eligibility traces
- reinforcement learning algorithms
- learning algorithm
- real time
- dynamic model
- dynamic programming
- supervised learning
- reinforcement learning methods
- model free
- learning process
- learning agent
- optimal control
- optimal policy
- dynamical systems
- multi agent
- machine learning
- action selection
- state action
- total reward
- learning agents
- policy gradient
- action space
- temporal difference
- markov chain
- feature selection
- social networks
- data mining