Discretizing Continuous Action Space for On-Policy Optimization
In this work, we show that discretizing action space for continuous control is a simple yet powerful technique for on-policy optimization. The explosion in the number of discrete actions can be efficiently addressed by a policy with factorized distribution across action dimensions. We show that the discrete policy achieves significant performance gains with state-of-the-art on-policy optimization algorithms (PPO, TRPO, ACKTR) especially on high-dimensional tasks with complex dynamics. Additionally, we show that an ordinal parameterization of the discrete distribution can introduce the inductive bias that encodes the natural ordering between discrete actions. This ordinal architecture further significantly improves the performance of PPO/TRPO.
Code (2)
Tasks
continuous-controlContinuous ControlInductive BiasMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning
For on-policy reinforcement learning, discretizing action space for continuous control can easily express multiple modes and is straightforward to optimize. However, without considering the inherent ordering between the …
continuous-controlContinuous Controlreinforcement-learningReinforcement LearningDeep Jump Q-Evaluation for Offline Policy Evaluation in Continuous Action Space
We consider off-policy evaluation (OPE) in continuous action domains, such as dynamic pricing and personalized dose finding. In OPE, one aims to learn the value under a new policy using historical data generated by a dif…
Off-policy evaluationQ-LearningDiscrete Sequential Prediction of Continuous Actions for Deep RL
It has long been assumed that high dimensional continuous control problems cannot be solved effectively by discretizing individual dimensions of the action space due to the exponentially large number of bins over which p…
continuous-controlContinuous ControlPredictionQ-Learning+1Adaptive Discretization for Continuous Control using Particle Filtering Policy Network
Controlling the movements of highly articulated agents and robots has been a long-standing challenge to model-free deep reinforcement learning. In this paper, we propose a simple, yet general, framework for improving the…
continuous-controlContinuous ControlDeep Reinforcement LearningBayesian Policy Optimization for Model Uncertainty
Addressing uncertainty is critical for autonomous systems to robustly adapt to the real world. We formulate the problem of model uncertainty as a continuous Bayes-Adaptive Markov Decision Process (BAMDP), where an agent …
model