An Empirical Comparison of Neural Architectures for Reinforcement Learning in Partially Observable Environments.
Denis SteckelmacherPeter VrancxPublished in: CoRR (2015)
Keyphrases
- partially observable environments
- neural architectures
- reinforcement learning
- reinforcement learning algorithms
- neural models
- inverse reinforcement learning
- partially observable
- neural network
- function approximation
- state space
- cooperative games
- markov decision processes
- partially observable markov decision processes
- multi agent
- model free
- temporal difference
- autonomous agents
- objective function
- learning algorithm