paper-with-me

Papers

Bayesian Soft Actor-Critic: A Directed Acyclic Strategy Graph Based Deep Reinforcement Learning

2022-08-11 · Qin Yang, Ramviyas Parasuraman

Adopting reasonable strategies is challenging but crucial for an intelligent agent with limited resources working in hazardous, unstructured, and dynamic environments to improve the system's utility, decrease the overall cost, and increase mission success probability. This paper proposes a novel directed acyclic strategy graph decomposition approach based on Bayesian chaining to separate an intricate policy into several simple sub-policies and organize their relationships as Bayesian strategy networks (BSN). We integrate this approach into the state-of-the-art DRL method -- soft actor-critic (SAC), and build the corresponding Bayesian soft actor-critic (BSAC) model by organizing several sub-policies as a joint policy. We compare our method against the state-of-the-art deep reinforcement learning algorithms on the standard continuous control benchmarks in the OpenAI Gym environment. The results demonstrate that the promising potential of the BSAC method significantly improves training efficiency.

📄 PDF Abstract BibTeX arXiv:2208.06033

Code (2)

herolab-uga/bsac 공식 구현 pytorch
rickyang2016/bayesian-soft-actor-critic--bsac 공식 구현 pytorch

Tasks

continuous-controlContinuous ControlDeep Reinforcement LearningOpenAI Gymreinforcement-learningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Clipped Double Q-learning 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Target Policy Smoothing Target Policy Smoothing is a regularization strategy for the value function in reinforcement learning. Deterministic policies can overfit to narrow peaks in the value…
Dilated Convolution 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Average Pooling 설명 없음
SAC 설명 없음

Similar Papers 제목 키워드 기반

On a hypergraph probabilistic graphical model

2018-11-20 · Mohammad Ali Javidian, Linyuan Lu, Marco Valtorta, Zhiyu Wang

We propose a directed acyclic hypergraph framework for a probabilistic graphical model that we call Bayesian hypergraphs. The space of directed acyclic hypergraphs is much larger than the space of chain graphs. Hence Bay…

model

Labeled Directed Acyclic Graphs: a generalization of context-specific independence in directed graphical models

2013-10-04 · Johan Pensar, Henrik Nyman, Timo Koski, Jukka Corander

We introduce a novel class of labeled directed acyclic graph (LDAG) models for finite sets of discrete variables. LDAGs generalize earlier proposals for allowing local structures in the conditional probability distributi…

FJMP: Factorized Joint Multi-Agent Motion Prediction over Learned Directed Acyclic Interaction Graphs

2022-11-27 · CVPR 2023 1 · Luke Rowe, Martin Ethier, Eli-Henry Dykhne, Krzysztof Czarnecki

Predicting the future motion of road agents is a critical task in an autonomous driving pipeline. In this work, we address the problem of generating a set of scene-level, or joint, future trajectory predictions in multi-…

Autonomous DrivingGraph Neural Networkmotion prediction

Context-Aware Bayesian Network Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning

2023-06-02 · Dingyang Chen, Qi Zhang

Executing actions in a correlated manner is a common strategy for human coordination that often leads to better cooperation, which is also potentially beneficial for cooperative multi-agent reinforcement learning (MARL).…

Multi-agent Reinforcement Learning

Testing Bayesian Networks

2016-12-09 · Clement Canonne, Ilias Diakonikolas, Daniel Kane, Alistair Stewart

This work initiates a systematic investigation of testing high-dimensional structured distributions by focusing on testing Bayesian networks -- the prototypical family of directed graphical models. A Bayesian network is …