Revisiting Sparse Rewards for Goal-Reaching Reinforcement Learning.
Gautham VasanYan WangFahim ShahriarJames BergstraMartin JägersandA. Rupam MahmoodPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- markov decision processes
- function approximation
- state space
- optimal policy
- supervised learning
- machine learning
- reinforcement learning algorithms
- sparse data
- learning algorithm
- learning process
- multi agent
- control policy
- dynamic programming
- high dimensional
- sparse coding
- model free
- reward function
- neural network