pomdp

Personal notes about scientific and research works on "Decision-Making for Autonomous Driving"

The DESPOT online POMDP solver

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/

Adaptive Attention Span for Reinforcement Learning

A Modern Probabilistic Model Checker

Efficient Point-Based POMDP Planning by Approximating

Python implementation of POMDP framework and PBVI & POMCP algorithms.

Baseline implementation of recurrent PPO using truncated BPTT

Modeling agents with probabilistic programs

Solving POMDP using Recurrent networks

Clean baseline implementation of PPO using an episodic TransformerXL memory

📚强化学习方向顶会文章（持续更新） | Top Conference Papers on Reinforcement Learning(RL)，including: NeurIPS, AAAI, IJCAI, ICML, AAMAS, ICLR, ICRA, etc.

Rich literature review and discussion on the implementation of "Hierarchical Decision-Making for Autonomous Driving"

Gym-like extensions for POMDP

Online Replanning in Belief Space for Partially Observable Task and Motion Problems

Deep Recurrent Q-Learning vs Deep Q Learning on a simple Partially Observable Markov Decision Process with Minecraft

Partially Observable Process Gym

Implementing a RL algorithm based upon a partially observable Markov decision process.

using recurrent networks(LSTM) to solve POMDPs