Simplifying Deep Reinforcement Learning via Self-Supervision.
Daochen ZhaKwei-Herng LaiKaixiong ZhouXia HuPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- model free
- learning algorithm
- state space
- markov decision processes
- robot control
- multi agent
- reinforcement learning algorithms
- active learning
- optimal policy
- policy search
- learning process
- real time
- deep learning
- temporal difference
- dynamic programming
- data mining
- action selection
- evolutionary algorithm
- learning capabilities
- information retrieval
- multi agent reinforcement learning
- database
- relational reinforcement learning