Tentative Exploration on Reinforcement Learning Algorithms for Stochastic Rewards.
Luis PeñaAntonio LaTorreJosé María Peña SánchezSascha OssowskiPublished in: HAIS (2009)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- markov decision processes
- reward function
- reward shaping
- model free
- state space
- total reward
- action selection
- temporal difference
- reinforcement learning problems
- reinforcement learning methods
- function approximation
- eligibility traces
- partially observable environments
- partially observable
- monte carlo
- finite state
- optimal policy
- policy search
- dynamic programming
- multiagent reinforcement learning
- control problems
- policy iteration
- learning algorithm
- multiple agents
- dynamic environments
- machine learning
- neural network
- policy gradient
- cost function