In-Context Reinforcement Learning for Variable Action Spaces.
Viacheslav SiniiAlexander NikulinVladislav KurenkovIlya ZismanSergey KolesnikovPublished in: CoRR (2023)
Keyphrases
- action space
- reinforcement learning
- continuous state
- state space
- state and action spaces
- markov decision processes
- real valued
- reinforcement learning methods
- learning algorithm
- function approximation
- control policies
- stochastic processes
- reinforcement learning algorithms
- action selection
- machine learning
- dynamic programming
- markov chain
- optimal solution
- policy search
- multi agent
- skill learning