Code for the paper "Functional Regularization for Reinforcement Learning via Learned Fourier Features"

Last update: Nov 11, 2022

Related tags

Overview

Reinforcement Learning with Learned Fourier Features

State-space Soft Actor-Critic Experiments

Move to the state-SAC-LFF repository.

cd state-SAC-LFF

To install the dependencies, use the provided environment.yml file

conda env create -f environment.yml

To run an experiment, the template for MLP and LFF experiments, respectively, are:

python main.py --policy PytorchSAC --env dm.quadruped.run --start_timesteps 5000 --hidden_dim 1024 --batch_size 1024 --n_hidden 3
python main.py --policy PytorchSAC --env dm.quadruped.run --start_timesteps 5000 --hidden_dim 1024 --batch_size 1024 --n_hidden 2 \
               --network_class FourierMLP --sigma 0.001 --fourier_dim 1024 --train_B --concatenate_fourier

The only thing that changes between the baseline is the number of hidden layers (we reduce by 1 to keep parameter count roughly the same), the network_class, the fourier_dim, sigma, train_B, and concatenate_fourier.

Image-space Soft Actor-Critic Experiments

Move to the image-SAC-LFF repository.

cd image-SAC-LFF

Install RAD dependencies:

conda env create -f conda_env.yml

To run an experiment, the template for CNN and CNN+LFF experiments, respectively, are:

python train.py --domain_name hopper --task_name hop --encoder_type fourier_pixel --action_repeat 4 \
                --num_eval_episodes 10 \--pre_transform_image_size 100 --image_size 84 --agent rad_sac \
                --frame_stack 3 --data_augs crop --critic_lr 1e-3 --actor_lr 1e-3 --eval_freq 10000 --batch_size 128 \
                --num_train_steps 1000000 --fourier_dim 128 --sigma 0.1 --train_B --concatenate_fourier
python train.py --domain_name hopper --task_name hop --encoder_type fair_pixel --action_repeat 4 \
                --num_eval_episodes 10 \--pre_transform_image_size 100 --image_size 84 --agent rad_sac \
                --frame_stack 3 --data_augs crop --critic_lr 1e-3 --actor_lr 1e-3 --eval_freq 10000 --batch_size 128 \
                --num_train_steps 1000000

Proximal Policy Optimization Experiments

Move to the state-PPO-LFF repository.

cd pytorch-a2c-ppo-acktr-gail

Install PPO dependencies:

conda env create -f environment.yml

To run an experiment, the template for MLP and LFF experiments, respectively, are:

python main.py --env-name Hopper-v2 --algo ppo --use-gae --log-interval 1 --num-steps 2048 --num-processes 1 \
               --lr 3e-4 --entropy-coef 0 --value-loss-coef 0.5 --ppo-epoch 10 --num-mini-batch 32 --gamma 0.99 \
               --gae-lambda 0.95 --num-env-steps 1000000 --use-linear-lr-decay --use-proper-time-limits \
               --hidden_dim 256 --network_class MLP --n_hidden 2 --seed 10
python main.py --env-name Hopper-v2 --algo ppo --use-gae --log-interval 1 --num-steps 2048 --num-processes 1 \
               --lr 3e-4 --entropy-coef 0 --value-loss-coef 0.5 --ppo-epoch 10 --num-mini-batch 32 --gamma 0.99 \
               --gae-lambda 0.95 --num-env-steps 1000000 --use-linear-lr-decay --use-proper-time-limits \
               --hidden_dim 256 --network_class FourierMLP --n_hidden 2 --sigma 0.01 --fourier_dim 64 \ 
               --concatenate_fourier --train_B --seed 10

Acknowledgements

We built the state-based SAC codebase off the TD3 repo by Fujimoto et al. We especially appreciated its lightweight bare-bones training loop. For the state-based SAC algorithm implementation and hyperparameters, we used this PyTorch SAC repo by Yarats and Kostrikov. For the SAC+RAD image-based experiments, we used the authors' implementation. Finally, we built off this PPO codebase by Ilya Kostrikov.

Code for the paper "Functional Regularization for Reinforcement Learning via Learned Fourier Features"

Related tags

Overview

Reinforcement Learning with Learned Fourier Features

State-space Soft Actor-Critic Experiments

Image-space Soft Actor-Critic Experiments

Proximal Policy Optimization Experiments

Acknowledgements

Owner

Alex Li

DIR-GNN - Discovering Invariant Rationales for Graph Neural Networks

[Arxiv preprint] Causality-inspired Single-source Domain Generalization for Medical Image Segmentation (code&data-processing pipeline)

User-friendly bulk RNAseq deconvolution using simulated annealing

Code for Talking Face Generation by Adversarially Disentangled Audio-Visual Representation (AAAI 2019)

Stock-history-display - something like a easy yearly review for your stock performance

ICSS - Interactive Continual Semantic Segmentation

The official implementation of ELSA: Enhanced Local Self-Attention for Vision Transformer

Art Project "Schrödinger's Game of Life"

Simultaneous Detection and Segmentation

nfelo: a power ranking, prediction, and betting model for the NFL

On-device wake word detection powered by deep learning.

Where-Got-Time - An NUS timetable generator which uses a genetic algorithm to optimise timetables to suit the needs of NUS students

Spatial Intention Maps for Multi-Agent Mobile Manipulation (ICRA 2021)

This is the code for Deformable Neural Radiance Fields, a.k.a. Nerfies.

A PyTorch implementation: "LASAFT-Net-v2: Listen, Attend and Separate by Attentively aggregating Frequency Transformation"

This repo contains the official code and pre-trained models for the Dynamic Vision Transformer (DVT).

GPU-Accelerated Deep Learning Library in Python

Ultra-Data-Efficient GAN Training: Drawing A Lottery Ticket First, Then Training It Toughly

Raptor-Multi-Tool - Raptor Multi Tool With Python

On-device speech-to-intent engine powered by deep learning