Predicting Multiple Actions for Stochastic Continuous Control
We introduce a new approach to estimate continuous actions using actor-critic algorithms for reinforcement learning problems. Policy gradient methods usually predict one continuous action estimate or parameters of a presumed distribution (most commonly Gaussian) for any given state which might not be optimal as it may not capture the complete description of the target distribution. Our approach instead predicts M actions with the policy network (actor) and then uniformly sample one action during training as well as testing at each state. This allows the agent to learn a simple stochastic policy that has an easy to compute expected return. In all experiments, this facilitates better exploration of the state space during training and converges to a better policy.
Code (0)
등록된 구현이 없습니다.
Tasks
continuous-controlContinuous ControlPolicy Gradient Methodsreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Multi-layered simulation relations for linear stochastic systems
The design of provably correct controllers for continuous-state stochastic systems crucially depends on approximate finite-state abstractions and their accuracy quantification. For this quantification, one generally uses…
Deep Sequence Learning for Video Anticipation: From Discrete and Deterministic to Continuous and Stochastic
Video anticipation is the task of predicting one/multiple future representation(s) given limited, partial observation. This is a challenging task due to the fact that given limited observation, the future representation …
Action AnticipationImplementing portfolio risk management and hedging in practice
In academic literature portfolio risk management and hedging are often versed in the language of stochastic control and Hamilton--Jacobi--Bellman~(HJB) equations in continuous time. In practice the continuous-time framew…
ManagementData-Driven Yet Formal Policy Synthesis for Stochastic Nonlinear Dynamical Systems
The automated synthesis of control policies for stochastic dynamical systems presents significant challenges. A standard approach is to construct a finite-state abstraction of the continuous system, typically represented…
Stochastic Actor-Executor-Critic for Image-to-Image Translation
Training a model-free deep reinforcement learning model to solve image-to-image translation is difficult since it involves high-dimensional continuous state and action spaces. In this paper, we draw inspiration from the …
continuous-controlContinuous ControlDeep Reinforcement LearningImage-to-Image Translation+4