λ-AC: Learning latent decision-aware models for reinforcement learning in continuous state-spaces.
Claas VoelckerArash AhmadianRomina AbachiIgor GilitschenskiAmir-massoud FarahmandPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- continuous state spaces
- state space
- learning algorithm
- learning process
- continuous state
- learning problems
- markov decision processes
- control problems
- supervised learning
- hidden variables
- action selection
- rl algorithms
- dynamic programming
- optimal control
- action space
- stochastic games
- hidden state