Informativeness of Reward Functions in Reinforcement Learning.
Rati DevidzeParameswaran KamalarubanAdish SinglaPublished in: AAMAS (2024)
Keyphrases
- reward function
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- policy search
- state space
- optimal policy
- inverse reinforcement learning
- partially observable
- multiple agents
- function approximation
- markov decision process
- multi agent
- model free
- transition model
- simple examples
- learning algorithm
- state variables
- initially unknown
- action selection
- pairwise
- temporal difference
- state action
- learning agents
- markov decision problems
- continuous state
- maximum likelihood
- dynamic programming
- machine learning