There are 7 repositories under pomdp topic.
Personal notes about scientific and research works on "Decision-Making for Autonomous Driving"
Simple (but often Strong) Baselines for POMDPs in PyTorch, ICML 2022
A framework to build and solve POMDP problems. Documentation: https://h2r.github.io/pomdp-py/
Clean baseline implementation of PPO using an episodic TransformerXL memory
Baseline implementation of recurrent PPO using truncated BPTT
A Modern Probabilistic Model Checker
Adaptive Attention Span for Reinforcement Learning
Python implementation of POMDP framework and PBVI & POMCP algorithms.
Challenging Memory-based Deep Reinforcement Learning Agents
Efficient Point-Based POMDP Planning by Approximating
Solving POMDP using Recurrent networks
Online Replanning in Belief Space for Partially Observable Task and Motion Problems
When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment, NeurIPS 2023 (oral)
Modeling agents with probabilistic programs
Official Implementation for the paper "SR-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World Models"
Rich literature review and discussion on the implementation of "Hierarchical Decision-Making for Autonomous Driving"
Implementing a Reinforcement Learning algorithm based upon a partially observable Markov decision process, applicable in modelling decision making.
Deep Recurrent Q-Learning vs Deep Q Learning on a simple Partially Observable Markov Decision Process with Minecraft
using recurrent networks(LSTM) to solve POMDPs
PBVI C++ Implementation for solving POMDPs
Benchmark for robotic tabletop manipulation memory-intensive tasks
This repository contains the code for RL for POMDPs through learning an Approximate Information State.
POMDP wrappers for OpenAI Gym
This repository presents an enhanced version of the HKUST-Aerial-Robotics/EPSILON project, migrated from ROS1 to ROS2 for improved performance and compatibility with modern autonomous driving frameworks.
[RAL 2023] transformer + reinforcement learning for navigation + POMPD
Sequential planner for large text based environments