MakarovIA/FPS

A3C & Episodic Learning

Open

#23 opened on Dec 1, 2016

View on GitHub
 (1 comment) (0 reactions) (1 assignee)C++ (1 fork)github user discovery
Deep Reinforcement Learninghelp wanted

Repository metrics

Stars
 (1 star)
PR merge metrics
 (PR metrics pending)

Description

Implement ASync RL 1602.01783.pdf asyncrl.pdf Read about Gorilla (Google RL Architecture) implementation

Implement algorithm from 1606.04460.pdf It will be used for Learning Policies for in-Team Tactics with Sparse Big Rewards

Contributor guide

Research direction
Study the provided papers (1602.01783, 1606.04460) on A3C and episodic control, then implement the algorithm in C++ within the FPS game environment, focusing on sparse reward handling for team tactics.
Tech stack
cpp
Domain
game devmachine learning
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Over 1 week
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Needs investigation
Prerequisites
C++Reinforcement Learning
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
10