Generalized Hidden Parameter MDPs Transferable Model-based RL in a Handful of Trials.
Christian F. PerezFelipe Petroski SuchTheofanis KaraletsosPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- markov decision processes
- model free
- state space
- optimal policy
- policy iteration
- markov decision process
- average reward
- function approximation
- state and action spaces
- multi agent
- learning algorithm
- factored mdps
- policy evaluation
- markov decision problems
- dynamic programming
- finite state
- policy search
- action space
- finite horizon
- parameter values
- partially observable
- action selection
- transfer function
- average cost
- control problems
- learning problems
- reinforcement learning algorithms
- temporal difference
- decision problems
- planning under uncertainty
- rl algorithms
- dynamical systems
- monte carlo
- continuous state spaces
- machine learning