Investigating Generalisation in Continuous Deep Reinforcement Learning.
Chenyang ZhaoOlivier SigaudFreek StulpTimothy M. HospedalesPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- action space
- continuous domains
- state space
- continuous state and action spaces
- function approximation
- optimal policy
- markov decision processes
- continuous state spaces
- reinforcement learning algorithms
- machine learning
- model free
- temporal difference
- multi agent
- artificial intelligence
- genetic algorithm
- dynamic programming
- hidden markov models
- piecewise linear
- learning process
- control problems
- knowledge base