An empirical study of implicit regularization in deep offline RL.
Çaglar GülçehreSrivatsan SrinivasanJakub SygnowskiGeorg OstrovskiMehrdad FarajtabarMatthew HoffmanRazvan PascanuArnaud DoucetPublished in: Trans. Mach. Learn. Res. (2022)
Keyphrases
- reinforcement learning
- state space
- regularization parameter
- multi agent
- optimal policy
- learning classifier systems
- real time
- regularization methods
- regularization framework
- model free
- smoothing parameter
- reinforcement learning algorithms
- parameter selection
- regularization term
- optimal control
- markov decision processes
- denoising
- data sets