Redeeming intrinsic rewards via constrained optimization.
Eric ChenZhang-Wei HongJoni PajarinenPulkit AgrawalPublished in: NeurIPS (2022)
Keyphrases
- constrained optimization
- constrained optimization problems
- constraint handling
- objective function
- penalty function
- unconstrained optimization
- augmented lagrangian
- reinforcement learning
- interval analysis
- iterative methods
- lagrange multipliers
- markov decision processes
- neural network
- penalty functions
- search algorithm