The statistical structures of reinforcement learning with asymmetric value updates
From MaRDI portal
Recommendations
- The relation between reinforcement learning parameters and the influence of reinforcement history on choice behavior
- Reinforcement-based vs. Belief-based Learning Models in Experimental Asymmetric-information Games
- Stochastic dynamics of reinforcement learning
- Statistical mechanics of reward-modulated learning in decision-making networks
- Risk-sensitive reinforcement learning
Cites work
- A new look at the statistical model identification
- Empirical priors for reinforcement learning models
- Estimating the dimension of a model
- How hierarchical models improve point estimates of model parameters at the individual level
- Model-based estimation of subjective values using choice tasks with probabilistic feedback
- The relation between reinforcement learning parameters and the influence of reinforcement history on choice behavior
Cited in
(3)- Biases in estimating the balance between model-free and model-based learning systems due to model misspecification
- The relation between reinforcement learning parameters and the influence of reinforcement history on choice behavior
- A Normative Account of Confirmation Bias During Reinforcement Learning
This page was built for publication: The statistical structures of reinforcement learning with asymmetric value updates
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1736016)
