Informativeness of Reward Functions in Reinforcement Learning.
Rati DevidzeParameswaran KamalarubanAdish SinglaPublished in: CoRR (2024)
Keyphrases
- reward function
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- policy search
- state space
- inverse reinforcement learning
- partially observable
- markov decision process
- optimal policy
- multiple agents
- function approximation
- learning agents
- transition probabilities
- temporal difference
- simple examples
- initially unknown
- machine learning
- multi agent
- average reward
- state action
- transition model
- state variables
- learning agent
- markov decision problems
- model free
- optimal control
- higher order
- control policies
- dynamic programming
- policy gradient
- active learning
- learning algorithm