The Primacy Bias in Deep Reinforcement Learning.
Evgenii NikishinMax SchwarzerPierluca D'OroPierre-Luc BaconAaron C. CourvillePublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- model free
- temporal difference
- direct policy search
- learning algorithm
- optimal policy
- markov decision processes
- dynamic programming
- state space
- reward function
- temporal difference learning
- learning capabilities
- robotic control
- multi agent reinforcement learning
- stochastic approximation
- reinforcement learning methods
- deep learning
- markov decision process
- robot control
- artificial neural networks
- neural network
- trade off
- unsupervised learning
- supervised learning