Stepsize Learning for Policy Gradient Methods in Contextual Markov Decision Processes.
Luca SabbioniFrancesco CordaMarcello RestelliPublished in: CoRR (2023)
Keyphrases
- markov decision processes
- reinforcement learning
- policy gradient methods
- state space
- step size
- stochastic games
- average reward
- optimal policy
- partially observable
- decision processes
- learning algorithm
- learning tasks
- policy gradient
- finite state
- supervised learning
- action selection
- temporal difference
- policy iteration
- reinforcement learning methods