Papers with Code 아카이브
Distributional Reinforcement Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Value distribution is the distribution of the random return received by a reinforcement learning agent. it been used for a specific purpose such as implementing risk-aware behaviour.
We have random return Z whose expectation is the value Q. This random return is also described by a recursive equation, but one of a distributional nature
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Improving Robustness via Risk Averse Distributional Reinforcement Learning
Distributional Reinforcement Learning with Ensembles
Millimeter Wave Communications with an Intelligent Reflector: Performance Optimization and Distributional Reinforcement Learning
Sample-based Distributional Policy Gradient
Distributional Reinforcement Learning for Energy-Based Sequential Models
Fully Parameterized Quantile Function for Distributional Reinforcement Learning
Estimating Risk and Uncertainty in Deep Reinforcement Learning
Stochastically Dominant Distributional Reinforcement Learning
Distributional Reinforcement Learning for Efficient Exploration
GAN-powered Deep Distributional Reinforcement Learning for Resource Management in Network Slicing
Statistics and Samples in Distributional Reinforcement Learning
Distributional reinforcement learning with linear function approximation
A Comparative Analysis of Expected and Distributional Reinforcement Learning
Information-Directed Exploration for Deep Reinforcement Learning
QUOTA: The Quantile Option Architecture for Reinforcement Learning
Implicit Quantile Networks for Distributional Reinforcement Learning
Nonlinear Distributional Gradient Temporal-Difference Learning
GAN Q-learning
Exploration by Distributional Reinforcement Learning
An Analysis of Categorical Distributional Reinforcement Learning
Distributional Reinforcement Learning with Quantile Regression
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.