anyrl-py - GitLite

KO | EN

gitlite — search

#python #hacktoberfest #ai #typescript #llm #go #android #deep-learning #awesome #pytorch #security #mcp #ios #openai

anyrl-py

(★ 157)

A reinforcement learning framework

파일 탐색기

최종 버전 다운로드 (.zip)

- - __init__.py
  - a2c.py
  - advantages.py
  - dqn.py
  - mpi.py
  - ppo.py
  - schedules.py
  - util.py
- - __init__.py
  - base.py
  - gym.py
- - __init__.py
  - base.py
  - dqn_dist.py
  - dqn_scalar.py
  - feedforward_ac.py
  - misc.py
  - recurrent_ac.py
  - util.py
- - __init__.py
  - list.py
  - logger.py
  - norm.py
  - players.py
  - replay.py
  - rollers.py
  - rollout.py
  - util.py
- - __init__.py
  - aggregate.py
  - base.py
  - binary.py
  - categorical.py
  - continuous.py
  - gym.py
- - __init__.py
  - test_ac_models.py
  - test_advantages.py
  - test_algos_util.py
  - test_dist_q.py
  - test_dists.py
  - test_env.py
  - test_mpi.py
  - test_norm.py
  - test_players.py
  - test_replay.py
  - test_rollers.py
  - test_schedules.py
  - test_spaces.py
  - test_utils.py
  - test_wrappers.py
  - util.py
- - __init__.py
  - atomic.py
  - ffmpeg.py
  - mpi.py
  - ppo.py
  - tf_state.py
- __init__.py
- atari_dqn.py
- cartpole.py
- cartpole_dqn.py
- cartpole_mpi.py
README.md
setup.py

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/unixpickle/anyrl-py

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd anyrl-py

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. 공식 설치 스크립트

쉬움 추천

사전 준비물

Python 3 pip 명령어를 쓰려면 Python이 필요합니다.

pip install anyrl

PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.

✅ 설치 후 새 터미널을 열고, 프로그램의 버전 확인 명령(예: --version)으로 정상 설치됐는지 확인하세요.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

3. Python

쉬움

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install anyrl

PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# anyrl-py

This is a Python remake (and makeover) of [anyrl](https://github.com/unixpickle/anyrl). It is a general-purpose library for Reinforcement Learning which aims to be as modular as possible.

# Installation

You can install anyrl with pip:

```
pip install anyrl
```

# APIs

There are several different sub-modules in anyrl:

* `models`: abstractions and concrete implementations of RL models. This includes actor-critic RNNs, MLPs, CNNs, etc. Takes care of sequence padding, BPTT, etc.
 * `envs`: APIs for dealing with environments, including wrappers and asynchronous environments.
 * `rollouts`: APIs for gathering and manipulating batches of episodes or partial episodes. Many RL algorithms include a "gather trajectories" step, and this sub-module fulfills that role.
 * `algos`: well-known learning algorithms like policy gradients or PPO. Also includes mini-algorithms like Generalized Advantage Estimation.
 * `spaces`: tools for using action and observation spaces. Includes parameterized probability distributions for implementing stochastic policies.

# Motivation

Currently, most RL code out there is very restricted and not properly decoupled. In contrast, anyrl aims to be extremely modular and flexible. The goal is to decouple agents, learning algorithms, trajectories, and things like GAE.

For example, anyrl decouples rollouts from the learning algorithm (when possible). This way, you can gather rollouts in several different ways and still feed the results into one learning algorithm. Further, and more obviously, you don't have to rewrite rollout code for every new RL algorithm you implement. However, algorithms like A3C and Evolution Strategies may have specific ways of performing rollouts that can't rely on the rollout API.

# Use of TensorFlow

This project relies on TensorFlow for models and training algorithms. However, anyrl APIs are framework-agnostic when possible. For example, the rollout API can be used with any policy, whether it's a TensorFlow neural network or a native-Python decision forest.

# Style

I use `autopep8` and `flake8`. Here is the command you can use to run autopep8:

```
autopep8 --recursive --in-place --max-line-length 100 .
```

I recommend the following flag for flake8: `--max-line-length=100`