Proximal Policy Optimization Algorithms.
John SchulmanFilip WolskiPrafulla DhariwalAlec RadfordOleg KlimovPublished in: CoRR (2017)
Keyphrases
- optimization problems
- learning algorithm
- optimization methods
- computationally efficient
- times faster
- data structure
- discrete optimization
- combinatorial optimization
- inverse reinforcement learning
- stochastic search
- recently developed
- benchmark datasets
- theoretical analysis
- worst case
- computational cost
- significant improvement
- lower bound
- computational complexity
- image segmentation