paper-with-me

Papers

Distributional Policy Optimization: An Alternative Approach for Continuous Control

2019-05-23 · NeurIPS 2019 12 · Chen Tessler, Guy Tennenholtz, Shie Mannor

We identify a fundamental problem in policy gradient-based methods in continuous control. As policy gradient methods require the agent's underlying probability distribution, they limit policy representation to parametric distribution classes. We show that optimizing over such sets results in local movement in the action space and thus convergence to sub-optimal solutions. We suggest a novel distributional framework, able to represent arbitrary distribution functions over the continuous action space. Using this framework, we construct a generative scheme, trained using an off-policy actor-critic paradigm, which we call the Generative Actor Critic (GAC). Compared to policy gradient methods, GAC does not require knowledge of the underlying probability distribution, thereby overcoming these limitations. Empirical evaluation shows that our approach is comparable and often surpasses current state-of-the-art baselines in continuous domains.

📄 PDF Abstract BibTeX arXiv:1905.09855

Code (3)

neurips-2019/GAC 공식 구현 pytorch
tesslerc/GAC 공식 구현 pytorch
gwbcho/dpo-replication tf

Tasks

continuous-controlContinuous ControlPolicy Gradient Methods

Similar Papers 제목 키워드 기반

Continuous Control Reinforcement Learning: Distributed Distributional DrQ Algorithms

2024-04-16 · Zehao Zhou

Distributed Distributional DrQ is a model-free and off-policy RL algorithm for continuous control tasks based on the state and observation of the agent, which is an actor-critic method with the data-augmentation and the …

continuous-controlContinuous ControlData Augmentationreinforcement-learning+1

Revisiting Gaussian mixture critics in off-policy reinforcement learning: a sample-based approach

2022-04-21 · Bobak Shahriari, Abbas Abdolmaleki, Arunkumar Byravan, Abe Friesen 외

Actor-critic algorithms that make use of distributional policy evaluation have frequently been shown to outperform their non-distributional counterparts on many challenging control tasks. Examples of this behavior includ…

continuous-controlContinuous Controlreinforcement-learningReinforcement Learning (RL)

Distributionally Robust Path Integral Control

2023-10-02 · Hyuk Park, Duo Zhou, Grani A. Hanasusanto, Takashi Tanaka

We consider a continuous-time continuous-space stochastic optimal control problem, where the controller lacks exact knowledge of the underlying diffusion process, relying instead on a finite set of historical disturbance…

Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control

2023-09-26 · NeurIPS 2023 11 · Nate Rahn, Pierluca D'Oro, Harley Wiltzer, Pierre-Luc Bacon 외

Deep reinforcement learning agents for continuous control are known to exhibit significant instability in their performance over time. In this work, we provide a fresh perspective on these behaviors by studying the retur…

continuous-controlContinuous ControlDeep Reinforcement Learning

Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors

2020-01-09 · Jingliang Duan, Yang Guan, Shengbo Eben Li, Yangang Ren 외

In reinforcement learning (RL), function approximation errors are known to easily lead to the Q-value overestimations, thus greatly reducing policy performance. This paper presents a distributional soft actor-critic (DSA…

continuous-controlContinuous ControlMuJoCoreinforcement-learning+2