astooke/rlpyt

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2278 stars · 326 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A PyTorch library providing modular, high-throughput implementations of deep reinforcement learning algorithms, covering policy gradient, deep Q-learning, and Q-function policy gradient families. It supports serial or parallelized experiments, multi-GPU optimization, recurrent agents, and OpenAI Gym-compatible environments.

Use cases

• train RL agents in PyTorch
• run PPO or A2C experiments
• implement DQN variants like Rainbow
• run parallel RL experiments on multiple GPUs
• train recurrent RL agents
• benchmark RL algorithms on Gym environments

When to choose

• you need a unified PyTorch codebase for model-free deep RL research
• you want high-throughput sampling and multi-GPU training on local hardware
• you need support for recurrent agents and prioritized replay buffers

When to avoid

• you need large-scale distributed RL with hundreds of GPUs
• you want actively maintained software with recent updates
• you need model-based RL or off-the-shelf pretrained agents

Facets

library · maturity maintenance

machine-learning reinforcement-learning gpu-computing reinforcement-learning machine-learning deep-learning python pytorch deep-rl policy-gradient dqn ppo a2c gym research-code research linux macos gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="astooke/rlpyt")