Reinforcement Learning with Depreciating Assets.
Taylor DohmenAshutosh TrivediPublished in: AAMAS (2023)
Keyphrases
- reinforcement learning
- state space
- function approximation
- markov decision processes
- learning algorithm
- robotic control
- reinforcement learning algorithms
- optimal policy
- markov decision process
- action selection
- temporal difference
- control problems
- direct policy search
- real world
- stochastic approximation
- temporal difference learning
- optimal control
- transfer learning
- dynamic environments
- markov chain
- data mining