What's Next if Reward is Enough? Insights for AGI from Animal Reinforcement Learning.
Shreya RajagopalPublished in: J. Artif. Gen. Intell. (2023)
Keyphrases
- reinforcement learning
- action selection
- artificial general intelligence
- intelligent systems
- function approximation
- reinforcement learning algorithms
- reward function
- eligibility traces
- machine learning
- state space
- partially observable environments
- temporal difference
- model free
- markov decision processes
- optimal policy
- general intelligence
- cognitive model
- data mining
- optimal control
- inverse reinforcement learning
- dynamic programming
- learning agent
- learning capabilities
- information processing
- multi agent
- robotic control
- partially observable
- average reward
- temporal difference learning
- reinforcement learning methods
- policy gradient
- markov chain
- monte carlo