# Khrylx/PyTorch-RL

PyTorch implementation of Deep Reinforcement Learning: Policy Gradient methods (TRPO, PPO, A2C) and Generative Adversarial Imitation Learning (GAIL). Fast Fisher vector product TRPO.

Repository: https://github.com/Khrylx/PyTorch-RL
Canonical: https://ross.abutalabs.com/products/pytorch-rl
Language: Python
License: MIT
License Family: permissive
Topics: reinforcement-learning, policy-gradient, pytorch-rl, proximal-policy-optimization, trpo, ppo, pytorch, a2c, generative-adversarial-network, fisher-vectors, deep-reinforcement-learning
Last push: 2021-02-09T16:17:59+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3242, "days_push": 2031, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1286, forks 192 (observed 2026-08-28T04:04:14.873811+00:00)

## What it is
A PyTorch library implementing deep reinforcement learning policy gradient algorithms (TRPO, PPO, A2C) and Generative Adversarial Imitation Learning (GAIL). It features fast Fisher vector product computation for TRPO and multiprocessing support for parallel sample collection.

## Use cases
- train a PPO agent on a gym environment
- run TRPO with fast Fisher vector products
- implement A2C for discrete and continuous action spaces
- do imitation learning from expert trajectories with GAIL
- collect RL samples in parallel with multiprocessing
- learn policy gradient algorithms from readable code

## When to choose
- you want clean, readable PyTorch implementations of TRPO, PPO, A2C, or GAIL
- you need efficient Fisher vector product computation for TRPO
- you are doing research or learning with OpenAI Gym / MuJoCo environments

## When to avoid
- you need a maintained library with recent PyTorch version support
- you want off-the-shelf support for modern RL algorithms like SAC or DQN
- you need production-grade distributed RL training at scale

## Facets
- artifact type: library
- maturity: maintenance
- function: reinforcement-learning, machine-learning, deep-learning
- domain: reinforcement-learning, machine-learning, deep-learning, robotics
- platform: python
- tags: pytorch, policy-gradient, trpo, ppo, a2c, gail, imitation-learning, gym, mujoco, fisher-vector-product, linux, macos, gpu

## Member repositories
- Khrylx/PyTorch-RL (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:14.873811+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:56:07.500530+00:00, confidence not recorded.
  - readme: https://github.com/Khrylx/PyTorch-RL (fetched 2026-08-28T04:04:14.873811+00:00, sha 4df9667a08a9)
- Data as of 2026-08-30T08:39:29.467469+00:00.