RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning.
Yan DuanJohn SchulmanXi ChenPeter L. BartlettIlya SutskeverPieter AbbeelPublished in: CoRR (2016)
Keyphrases
- reinforcement learning
- function approximation
- temporal difference
- state space
- markov decision processes
- reinforcement learning algorithms
- model free
- optimal policy
- multi agent
- dynamic programming
- direct policy search
- control problems
- temporal difference learning
- markov decision process
- continuous state
- reinforcement learning methods
- approximate dynamic programming
- partially observable
- optimal control
- learning problems
- rl algorithms
- autonomous learning
- policy search
- action selection
- machine learning
- transfer learning
- supervised learning
- learning algorithm