The Primacy Bias in Deep Reinforcement Learning.
Evgenii NikishinMax SchwarzerPierluca D'OroPierre-Luc BaconAaron C. CourvillePublished in: ICML (2022)
Keyphrases
- reinforcement learning
- function approximation
- model free
- reinforcement learning algorithms
- state space
- optimal policy
- markov decision processes
- temporal difference
- learning algorithm
- artificial intelligence
- multi agent
- learning process
- optimal control
- variance reduction
- deep learning
- direct policy search
- multi agent reinforcement learning
- robotic control
- information retrieval
- control problems
- partially observable
- learning classifier systems
- learning problems
- semi supervised
- genetic algorithm