Continual Reinforcement Learning in 3D Non-stationary Environments

by   Vincenzo Lomonaco, et al.
University of Bologna

High-dimensional always-changing environments constitute a hard challenge for current reinforcement learning techniques. Artificial agents, nowadays, are often trained off-line in very static and controlled conditions in simulation such that training observations can be thought as sampled i.i.d. from the entire observations space. However, in real world settings, the environment is often non-stationary and subject to unpredictable, frequent changes. In this paper we propose and openly release CRLMaze, a new benchmark for learning continually through reinforcement in a complex 3D non-stationary task based on ViZDoom and subject to several environmental changes. Then, we introduce an end-to-end model-free continual reinforcement learning strategy showing competitive results with respect to four different baselines and not requiring any access to additional supervised signals, previously encountered environmental conditions or observations.


page 3

page 4


Double Meta-Learning for Data Efficient Policy Optimization in Non-Stationary Environments

We are interested in learning models of non-stationary environments, whi...

The complexity of non-stationary reinforcement learning

The problem of continual learning in the domain of reinforcement learnin...

Sub-Structural Niching in Non-Stationary Environments

Niching enables a genetic algorithm (GA) to maintain diversity in a popu...

Tackling Non-Stationarity in Reinforcement Learning via Causal-Origin Representation

In real-world scenarios, the application of reinforcement learning is si...

Continual Prototype Evolution: Learning Online from Non-Stationary Data Streams

As learning from non-stationary streams of data has been proven a challe...

AID: Open-source Anechoic Interferer Dataset

A dataset of anechoic recordings of various sound sources encountered in...

Code Repositories


Continual Reinforcement Learning in 3D Non-stationary Environments

view repo

Please sign up or login with your details

Forgot password? Click here to reset