On the Practical Consistency of Meta-Reinforcement Learning Algorithms.
Zheng XiongLuisa M. ZintgrafJacob BeckRisto VuorioShimon WhitesonPublished in: CoRR (2021)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- state space
- model free
- markov decision processes
- eligibility traces
- temporal difference
- learning algorithm
- reinforcement learning methods
- reinforcement learning problems
- function approximation
- stochastic games
- dynamic environments
- reward shaping
- policy search
- function approximators
- reward function