Decoupling regularization from the action space.
Sobhan MohammadpourEmma FrejingerPierre-Luc BaconPublished in: ICLR (2024)
Keyphrases
- action space
- state space
- markov decision processes
- real valued
- reinforcement learning
- state and action spaces
- action selection
- stochastic processes
- single agent
- state action
- continuous state spaces
- semi supervised
- dynamic environments
- optimal policy
- heuristic search
- probability distribution
- search algorithm
- data mining