Technical Report: The Policy Graph Improvement Algorithm

2020-09-04 · Joni Pajarinen

Optimizing a partially observable Markov decision process (POMDP) policy is challenging. The policy graph improvement (PGI) algorithm for POMDPs represents the policy as a fixed size policy graph and improves the policy monotonically. Due to the fixed policy size, computation time for each improvement iteration is known in advance. Moreover, the method allows for compact understandable policies. This report describes the technical details of the PGI [1] and particle based PGI [2] algorithms for POMDPs in a more accessible way than [1] or [2] allowing practitioners and students to understand and implement the algorithms.

📄 PDF Abstract BibTeX arXiv:2009.02164

Code (0)

등록된 구현이 없습니다.

Spectral Toolkit of Algorithms for Graphs: Technical Report (2)

2024-06-06 · Peter Macgregor, He Sun

Spectral Toolkit of Algorithms for Graphs (STAG) is an open-source library for efficient graph algorithms. This technical report presents the newly implemented component on locality sensitive hashing, kernel density esti…

Clustering Density Estimation

Spectral Toolkit of Algorithms for Graphs: Technical Report (1)

2023-04-05 · Peter Macgregor, He Sun

Spectral Toolkit of Algorithms for Graphs (STAG) is an open-source library for efficient spectral graph algorithms, and its development starts in September 2022. We have so far finished the component on local graph clust…

Clustering Graph Clustering

Secrets of RLHF in Large Language Models Part I: PPO

2023-07-11 · Rui Zheng, Shihan Dou, Songyang Gao, Yuan Hua 외

Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. Its primary objective is to function as a human-centric (helpful, honest, and harmless) assistant. Alignmen…

Making Reinforcement Learning Work on Swimmer

2022-08-16 · Maël Franceschetti, Coline Lacoux, Ryan Ohouens, Antonin Raffin 외

The SWIMMER environment is a standard benchmark in reinforcement learning (RL). In particular, it is often used in papers comparing or combining RL methods with direct policy search methods such as genetic algorithms or …

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Multi-Goal Reinforcement Learning environments for simulated Franka Emika Panda robot

2021-06-25 · Quentin Gallouédec, Nicolas Cazin, Emmanuel Dellandréa, Liming Chen

This technical report presents panda-gym, a set Reinforcement Learning (RL) environments for the Franka Emika Panda robot integrated with OpenAI Gym. Five tasks are included: reach, push, slide, pick & place and stack. T…

Multi-Goal Reinforcement Learning OpenAI Gym reinforcement-learning Reinforcement Learning (RL)