Rich-Observation Reinforcement Learning with Continuous Latent Dynamics.
Yuda SongLili WuDylan J. FosterAkshay KrishnamurthyPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- action space
- state space
- function approximation
- learning algorithm
- neural dynamics
- continuous state spaces
- reinforcement learning algorithms
- latent variables
- dynamical systems
- dynamic model
- markov decision processes
- dynamic programming
- continuous state and action spaces
- temporal difference learning
- robotic control
- optimal policy
- temporal difference
- semi supervised
- continuous domains
- control problems
- stochastic approximation
- high dimensional
- real world