SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1707.04402 · 2017

Lenient Multi-Agent Deep Reinforcement Learning

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Much of the success of single agent deep reinforcement learning (DRL) in recent years can be attributed to the use of experience replay memories (ERM), which allow Deep Q-Networks (DQNs) to be trained efficiently through sampling stored state transitions. However, care is required when using ERMs for multi-agent deep reinforcement learning (MA-DRL), as stored transitions can become outdated because agents update their policies in parallel [11]. In this work we apply leniency [23] to MA-DRL. Lenient agents map state-action pairs to decaying temperature values that control the amount of leniency applied towards negative policy updates that are sampled from the ERM. This introduces optimism in the value-function update, and has been shown to facilitate cooperation in tabular fully-cooperative multi-agent reinforcement learning problems. We evaluate our Lenient-DQN (LDQN) empirically against the related Hysteretic-DQN (HDQN) algorithm [22] as well as a modified version we call scheduled-HDQN, that uses average reward learning near terminal states. Evaluations take place in extended variations of the Coordinated Multi-Agent Object Transportation Problem (CMOTP) [8] which include fully-cooperative sub-tasks and stochastic rewards. We find that LDQN agents are more likely to converge to the optimal policy in a stochastic reward CMOTP compared to standard and scheduled-HDQN agents.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1707.04402")
get_code_for_paper("1707.04402")
have("1707.04402")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1707.04402.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1707.04402.svg)](https://syntology.ai/paper/1707.04402)

Connect an agent — have() is free.