Discovering Temporally-Aware Reinforcement Learning Algorithms.
Matthew Thomas JacksonChris LuLouis KirschRobert Tjarko LangeShimon WhitesonJakob Nicolaus FoersterPublished in: ICLR (2024)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- state space
- markov decision processes
- model free
- reinforcement learning problems
- reinforcement learning methods
- eligibility traces
- temporal difference
- function approximation
- learning algorithm
- dynamic environments
- reward function
- partially observable environments
- policy search
- stochastic games
- multi agent
- control problems
- policy gradient
- learning experience
- machine learning
- neural network