Using Natural Language for Reward Shaping in Reinforcement Learning.
Prasoon GoyalScott NiekumRaymond J. MooneyPublished in: IJCAI (2019)
Keyphrases
- reward shaping
- reinforcement learning
- natural language
- reinforcement learning algorithms
- complex domains
- state space
- machine learning
- knowledge representation
- markov decision processes
- function approximation
- markov decision problems
- optimal policy
- multi agent
- model free
- dynamic programming
- multi agent systems
- partially observable markov decision processes
- optimal control
- complex environments
- reward function
- policy iteration