A Simple Example for Imitation Learning with Dataset Aggregation (DAGGER) on Torcs Env

Last update: Nov 23, 2022

Overview

Imitation Learning with Dataset Aggregation (DAGGER) on Torcs Env

This repository implements a simple algorithm for imitation learning: DAGGER. In this example, the agent only learns to control the steer [-1, 1], the speed is computed automatically in gym_torcs.TorcsEnv.

Requirements

Ubuntu (I only test on this)
Python 3
TensorLayer and TensorFlow
Gym-Torcs

Setting Up

It is a little bit boring to set up the environment, but any incorrect configurations will lead to FAILURE. After installing Gym-Torcs, please follow the instructions to confirm everything work well:

Open a terminal:
- Run sudo torcs -vision to start a game
- Race --> Practice --> Configure Race: set the driver to scr_server 1 instead of player
- Open Torcs server by selecting Race --> Practice --> New Race: This should result that Torcs keeps a blue screen with several text information.
Open another terminal:
- Run python snakeoil3_gym.py on another terminal, it will shows how the fake AI control the car.
- Press F2 to see the driver view.
Set image size to 64x64x3:
- The model is trained on 64x64 RGB observation.
- Run sudo torcs -vision to start a game
- Options --> Display --> select 64x64 --> Apply

Usage

Make sure everything above work well and then run:

python dagger.py

It will start a Torcs server at the beginning of every episode, and terminate the server when the car crashs or the speed is too low. Note that, the self-contained gym_torcs.py is modified from Gym-Torcs, you can try different settings (like default speed, terminated speed) by modifying it.

Results

After Episode 1, the car crashes after 315 steps.

After Episode 3, the car does not crash anymore !!!

The number of steps and episodes might vary depending on the parameters initialization.

ENJOY !

You might also like...

PyTorch implementation of SMODICE: Versatile Offline Imitation Learning via State Occupancy Matching

SMODICE: Versatile Offline Imitation Learning via State Occupancy Matching This is the official PyTorch implementation of SMODICE: Versatile Offline I

14 Aug 30, 2022

Neon-erc20-example - Example of creating SPL token and wrapping it with ERC20 interface in Neon EVM

Example of wrapping SPL token by ERC2-20 interface in Neon Requirements Install

7 Mar 28, 2022

Example-custom-ml-block-keras - Custom Keras ML block example for Edge Impulse

Custom Keras ML block example for Edge Impulse This repository is an example on

8 Nov 2, 2022

Python-kafka-reset-consumergroup-offset-example - Python Kafka reset consumergroup offset example

Python Kafka reset consumergroup offset example This is a simple example of how

1 Feb 16, 2022

Pytorch code for "State-only Imitation with Transition Dynamics Mismatch" (ICLR 2020)

This repo contains code for our paper State-only Imitation with Transition Dynamics Mismatch published at ICLR 2020. The code heavily uses the RL mach

20 Sep 8, 2022

[CVPR 2022] PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision (Oral)

PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision Kehong Gong*, Bingbing Li*, Jianfeng Zhang*, Ta

256 Dec 28, 2022

Learning to Estimate Hidden Motions with Global Motion Aggregation

Learning to Estimate Hidden Motions with Global Motion Aggregation (GMA) This repository contains the source code for our paper: Learning to Estimate

221 Dec 18, 2022

Official repository for the CVPR 2021 paper "Learning Feature Aggregation for Deep 3D Morphable Models"

Deep3DMM Official repository for the CVPR 2021 paper Learning Feature Aggregation for Deep 3D Morphable Models. Requirements This code is tested on Py

38 Dec 27, 2022

A pytorch reproduction of { Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation }.

A PyTorch Reproduction of HCN Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation. Ch

210 Dec 31, 2022

Comments

About the convergence and overfit

Hi, thanks for your job and I rewrite it using Keras in the attitude of learning. And I use your recommended hyper-parameters but when I run my program it's apt to overfit. Later on, I change the hyper-parameters , add BN and explicit initialization function of each layer. But it's still overfitting and the car runs 700 steps at the best time but still can't go through the all track. I have spent more than two weeks to tune it. I'm so confused of the tuning, why the same hyper-parameters can't achieve the same result? Why the network is so apt to overfit? For convenience, I update my programmer imitationLearning.py Can you give me some idea? Than you in advance.

opened by marooncn 0

A Simple Example for Imitation Learning with Dataset Aggregation (DAGGER) on Torcs Env

Related tags

Overview

Imitation Learning with Dataset Aggregation (DAGGER) on Torcs Env

Requirements

Setting Up

Usage

Results

You might also like...

PyTorch implementation of SMODICE: Versatile Offline Imitation Learning via State Occupancy Matching

Neon-erc20-example - Example of creating SPL token and wrapping it with ERC20 interface in Neon EVM

Example-custom-ml-block-keras - Custom Keras ML block example for Edge Impulse

Python-kafka-reset-consumergroup-offset-example - Python Kafka reset consumergroup offset example

Pytorch code for "State-only Imitation with Transition Dynamics Mismatch" (ICLR 2020)

[CVPR 2022] PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision (Oral)

Learning to Estimate Hidden Motions with Global Motion Aggregation

Official repository for the CVPR 2021 paper "Learning Feature Aggregation for Deep 3D Morphable Models"

A pytorch reproduction of { Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation }.

Comments

About the convergence and overfit

Releases(0.1)

0.1(Aug 10, 2017)

Owner

Hao

Code for Deep Single-image Portrait Image Relighting

Implementation of experiments in the paper Clockwork Variational Autoencoders (project website) using JAX and Flax

Exploring Versatile Prior for Human Motion via Motion Frequency Guidance (3DV2021)

Simple implementation of Mobile-Former on Pytorch

Deep learning model for EEG artifact removal

Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms

OREO: Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning (NeurIPS 2021)

Liver segmentation using MONAI and pytorch

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

Code for Mesh Convolution Using a Learned Kernel Basis

WebUAV-3M: A Benchmark Unveiling the Power of Million-Scale Deep UAV Tracking

[ICCV21] Self-Calibrating Neural Radiance Fields

Official Pytorch implementation of paper "Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images"

This repository is for EMNLP 2021 paper: It is Not as Good as You Think! Evaluating Simultaneous Machine Translation on Interpretation Data

Optimal space decomposition based-product quantization for approximate nearest neighbor search

An SE(3)-invariant autoencoder for generating the periodic structure of materials

SustainBench: Benchmarks for Monitoring the Sustainable Development Goals with Machine Learning

An Agnostic Computer Vision Framework - Pluggable to any Training Library: Fastai, Pytorch-Lightning with more to come

Code for "The Intrinsic Dimension of Images and Its Impact on Learning" - ICLR 2021 Spotlight

This repo contains the pytorch implementation for Dynamic Concept Learner (accepted by ICLR 2021).