Adapting Double Q-Learning for Continuous Reinforcement Learning.
Arsenii KuznetsovPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- continuous state and action spaces
- function approximation
- continuous state spaces
- reinforcement learning algorithms
- action space
- state space
- model free
- optimal policy
- learning algorithm
- multi agent
- continuous state
- action selection
- temporal difference learning
- state action
- markov decision processes
- state action space
- control problems
- stochastic approximation
- machine learning
- temporal difference
- eligibility traces
- multi agent reinforcement learning
- function approximators
- rl algorithms
- supervised learning
- learning process
- transfer learning
- real valued
- optimal control
- learning rate
- mobile robot
- partially observable
- dynamic programming
- policy search
- relational reinforcement learning
- learning classifier systems