Benchmark for Out-of-Distribution Detection in Deep Reinforcement Learning.
Aaqib Parvez MohammedMatias Valdenegro-ToroPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- real world
- detection accuracy
- automatic detection
- detection algorithm
- detection scheme
- detection rate
- markov decision processes
- detection method
- object detection
- state space
- false positives
- learning algorithm
- information retrieval
- function approximation
- uniformly distributed
- optimal policy
- random variables
- transfer learning
- multi agent
- false alarms
- machine learning
- temporal difference
- reinforcement learning algorithms
- real time