partially-observable-environment

Partially Observable Process Gym

POMDP wrappers for OpenAI Gym

Certainty-Equivalent Expectation Maximization: a scalable algorithm for system identification of partially observed systems

A robot motion planning simulator that can efficiently navigate partially observable environments using deep learning

Multi-agent pursuit in matrix world (pursuitMW)

Heuristic Search Value Iteration for One-Sided Partially Observable Stochastic Games

Scallable partially observable and/or non-Markovian gridworld for planning or reinforcement learning

Application of Reinforcement Learning algorithms (DQN,DRQN,PPO,A2C) to gym's MountainCar-v0

Recurrent Policies for Handling Partially Observable Environments

Explored Reinforcement Learning algorithms in a partially observable, multi-agent environment. Focused on Joint-Action Learning leveraging Game-Theoretic solution concepts to study agent coordination and strategic interactions.

An agent being trained to find its way in a stochastic and partially observable maze using SARSA and Q-Learning algorithms.

Virtual reality (VR) environment for studying human-agent decision making.

Forward A* and Adaptive A* for navigation in partially known environments

Implementation of "A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes" (ICML)

cleaning agent where the environment is partially observable

An implementation of Genetic Programming using Indexed Memory to solve the Partially Observable CartPole problem