scholarly journals What do reinforcement learning models measure? Interpreting model parameters in cognition and neuroscience

2021 ◽  
Vol 41 ◽  
pp. 128-137
Author(s):  
Maria K Eckstein ◽  
Linda Wilbrecht ◽  
Anne GE Collins
Keyword(s):  
Reinforcement Learning ◽  
Model Parameters ◽  
Learning Models ◽  
Reinforcement Learning Models

Bayes factors for reinforcement-learning models of the Iowa gambling task.

Decision ◽  
2016 ◽  
Vol 3 (2) ◽  
pp. 115-131 ◽  
Author(s):  
Helen Steingroever ◽  
Ruud Wetzels ◽  
Eric-Jan Wagenmakers
Keyword(s):  
Reinforcement Learning ◽  
Iowa Gambling Task ◽  
Bayes Factors ◽  
Gambling Task ◽  
Learning Models ◽  
Reinforcement Learning Models

scholarly journals Test-retest reliability of canonical reinforcement learning models

2019 ◽  
Author(s):  
Laura Weidinger ◽  
Andrea Gradassi ◽  
Lucas Molleman ◽  
Wouter van den Bos
Keyword(s):  
Reinforcement Learning ◽  
Learning Models ◽  
Retest Reliability ◽  
Reinforcement Learning Models ◽  
Test Retest Reliability

scholarly journals ERLP: Ensembles of Reinforcement Learning Policies (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13905-13906
Author(s):  
Rohan Saphal ◽  
Balaraman Ravindran ◽  
Dheevatsa Mudigere ◽  
Sasikanth Avancha ◽  
Bharat Kaul
Keyword(s):  
Reinforcement Learning ◽  
State Of The Art ◽  
Multiple Models ◽  
Model Parameters ◽  
Continuous Control ◽  
Sample Complexity ◽  
Local Minima ◽  
Single Model ◽  
Learning Policies ◽  
Reinforcement Learning Models

Reinforcement learning algorithms are sensitive to hyper-parameters and require tuning and tweaking for specific environments for improving performance. Ensembles of reinforcement learning models on the other hand are known to be much more robust and stable. However, training multiple models independently on an environment suffers from high sample complexity. We present here a methodology to create multiple models from a single training instance that can be used in an ensemble through directed perturbation of the model parameters at regular intervals. This allows training a single model that converges to several local minima during the optimization process as a result of the perturbation. By saving the model parameters at each such instance, we obtain multiple policies during training that are ensembled during evaluation. We evaluate our approach on challenging discrete and continuous control tasks and also discuss various ensembling strategies. Our framework is substantially sample efficient, computationally inexpensive and is seen to outperform state of the art (SOTA) approaches

Sign in / Sign up

Export Citation Format

Share Document