Continual Match Based Training in Pommerman: Technical Report

by   Peng Peng, et al.

Continual learning is the ability of agents to improve their capacities throughout multiple tasks continually. While recent works in the literature of continual learning mostly focused on developing either particular loss functions or specialized structures of neural network explaining the episodic memory or neural plasticity, we study continual learning from the perspective of the training mechanism. Specifically, we propose a COnitnual Match BAsed Training (COMBAT) framework for training a population of advantage-actor-critic (A2C) agents in Pommerman, a partially observable multi-agent environment with no communication. Following the COMBAT framework, we trained an agent, namely, Navocado, that won the title of the top 1 learning agent in the NeurIPS 2018 Pommerman Competition. Two critical features of our agent are worth mentioning. Firstly, our agent did not learn from any demonstrations. Secondly, our agent is highly reproducible. As a technical report, we articulate the design of state space, action space, reward, and most importantly, the COMBAT framework for our Pommerman agent. We show in the experiments that Pommerman is a perfect environment for studying continual learning, and the agent can improve its performance by continually learning new skills without forgetting the old ones. Finally, the result in the Pommerman Competition verifies the robustness of our agent when competing with various opponents.


page 1

page 7

page 8


Unicorn: Continual Learning with a Universal, Off-policy Agent

Some real-world domains are best characterized as a single task, but for...

Continual Learning for Robotics

Continual learning (CL) is a particular machine learning paradigm where ...

Continual Reinforcement Learning with Multi-Timescale Replay

In this paper, we propose a multi-timescale replay (MTR) buffer for impr...

A Study on Efficiency in Continual Learning Inspired by Human Learning

Humans are efficient continual learning systems; we continually learn ne...

AI Autonomy: Self-Initiation, Adaptation and Continual Learning

As more and more AI agents are used in practice, it is time to think abo...

Multi-lingual agents through multi-headed neural networks

This paper considers cooperative Multi-Agent Reinforcement Learning, foc...

Embodied Continual Learning Across Developmental Time Via Developmental Braitenberg Vehicles

There is much to learn through synthesis of Developmental Biology, Cogni...

Please sign up or login with your details

Forgot password? Click here to reset