Deep Reinforcement Learning with Weighted Q-Learning.
Andrea CiniCarlo D'EramoJan PetersCesare AlippiPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- state space
- multi agent
- stochastic approximation
- markov decision processes
- control problems
- model free
- optimal policy
- learning algorithm
- temporal difference learning
- multi agent reinforcement learning
- relational reinforcement learning
- state action space
- machine learning
- temporal difference
- action selection
- learning process
- dynamic programming
- supervised learning
- reinforcement learning methods
- function approximators
- learning problems
- rl algorithms
- transfer learning
- actor critic
- continuous state spaces
- continuous state and action spaces
- state action
- real robot
- continuous state
- single agent
- optimal control
- eligibility traces
- partially observable