On the Reliability and Generalizability of Brain-inspired Reinforcement Learning Algorithms.
Dongjae KimJeehang LeeJae Hoon ShinMinsu Abel YangSang Wan LeePublished in: CoRR (2020)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- state space
- markov decision processes
- model free
- reinforcement learning problems
- eligibility traces
- temporal difference
- reinforcement learning methods
- learning algorithm
- function approximation
- partially observable environments
- policy search
- optimal policy
- dynamic environments
- partially observable
- multi agent
- transition probabilities
- learning experience
- action space
- stochastic games
- dynamic programming
- machine learning
- reward shaping