Stabilizing Transformers for Reinforcement Learning.
Emilio ParisottoH. Francis SongJack W. RaeRazvan PascanuÇaglar GülçehreSiddhant M. JayakumarMax JaderbergRaphael Lopez KaufmanAidan ClarkSeb NouryMatthew M. BotvinickNicolas HeessRaia HadsellPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- state space
- temporal difference
- multi agent reinforcement learning
- nonlinear systems
- markov decision processes
- optimal policy
- reinforcement learning algorithms
- dynamic programming
- transfer learning
- control problems
- robotic control
- model free
- multi agent
- temporal difference learning
- partial discharge
- stochastic approximation
- relational reinforcement learning
- database
- action space
- supervised learning
- least squares
- learning process
- expert systems
- data sets