Evolving Reinforcement Learning Algorithms.
John D. Co-ReyesYingjie MiaoDaiyi PengEsteban RealQuoc V. LeSergey LevineHonglak LeeAleksandra FaustPublished in: ICLR (2021)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- state space
- markov decision processes
- model free
- reinforcement learning problems
- reinforcement learning methods
- eligibility traces
- temporal difference
- partially observable environments
- function approximation
- learning algorithm
- stochastic games
- dynamic environments
- neural network
- policy iteration
- policy search
- multiagent systems
- machine learning algorithms
- multiagent reinforcement learning