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

Simple (but often Strong) Baselines for POMDPs in PyTorch, ICML 2022

The DESPOT online POMDP solver

A framework to build and solve POMDP problems. Documentation: https://h2r.github.io/pomdp-py/

Partially Observable Process Gym

Clean baseline implementation of PPO using an episodic TransformerXL memory

A Modern Probabilistic Model Checker

Adaptive Attention Span for Reinforcement Learning

Baseline implementation of recurrent PPO using truncated BPTT

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

Modeling agents with probabilistic programs

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)

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

Gym-like extensions for POMDP

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

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