Beating Atari with Natural Language Guided Reinforcement Learning.
Russell KaplanChristopher SauerAlexander SosaPublished in: CoRR (2017)
Keyphrases
- reinforcement learning
- linear value function approximation
- natural language
- reinforcement learning problems
- machine learning
- linear programming
- reinforcement learning algorithms
- function approximation
- multi agent
- state space
- markov decision problems
- markov games
- markov decision processes
- learning process
- optimal policy
- temporal difference
- learning algorithm
- markov decision process
- control problems
- partially observable markov decision processes
- learning capabilities
- action space
- model free
- optimal control
- supervised learning
- cooperative