Tags / Machine learning /
Reinforcement learning
A library, environment, or agent implementation for reinforcement learning; not RLHF tools for LLMs.
Repositories
27
Net stars gained, last 7 days
+677
Top-level Tag
Net stars gained each day, last 90 days
Peak days
- 1
Sep 16, 2026 +642 net stars (median day +88)
- Human-Agent-Society/reef+589 (92%)
- DLR-RM/stable-baselines3+12 (2%)
- AI4Finance-Foundation/FinRL+9 (1%)
- 2
Sep 17, 2026 +799 net stars (median day +88)
- Human-Agent-Society/reef+768 (96%)
- DLR-RM/stable-baselines3+6 (1%)
- Unity-Technologies/ml-agents+6 (1%)
- 3
Sep 24, 2026 +687 net stars (median day +88)
- Human-Agent-Society/reef+632 (92%)
Published v0.1.0 on Sep 23, 2026
- tensortrade-org/tensortrade+22 (3%)
- AI4Finance-Foundation/FinRL+11 (2%)
- 4
Sep 26, 2026 +588 net stars (median day +88)
- Human-Agent-Society/reef+562 (96%)
Published v0.1.1 on Sep 25, 2026
- AI4Finance-Foundation/FinRL+11 (2%)
- tensortrade-org/tensortrade+3 (1%)
- 5
Sep 27, 2026 +521 net stars (median day +88)
- Human-Agent-Society/reef+485 (93%)
- AI4Finance-Foundation/FinRL+10 (2%)
- vwxyzjn/cleanrl+6 (1%)
A peak day has at least 2 times the net stars of the median day of this chart, and at least 100 more. For each peak day, the list shows the repositories that gained the most net stars that day. It also shows their GitHub releases of that day or the day before (UTC), and their creation date when it was 14 days or less before. These events occur near the same day. They do not show why the stars came.
Largest
Most stars in total now.
- openai/gymarchived · 37K
description:
A toolkit for developing and comparing reinforcement learning algorithms.
description:
enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
readme:
FinRL is the original open-source framework for financial reinforcement learning, organized around three core layers:
readme:
OpenAI Baselines is a set of high-quality implementations of reinforcement learning algorithms.
readme:
The reinforcement learning agents train on environments defined in the OpenAI gym.
readme:
Stable Baselines3 (SB3) is a set of reliable implementations of reinforcement learning algorithms in PyTorch.
description:
A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
description:
An elegant PyTorch deep reinforcement learning library.
description:
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
readme:
CleanRL is a Deep Reinforcement Learning library that provides high-quality single-file implementation with research-friendly features.
Newest Admissions
Entered the index by the rising rule, newest first.
readme:
Unitree G1 29DOF 的分层导航强化学习：`LiDAR CNN → 空间 Transformer → SRU → [vx, vy, wz]`。
readme:
Connect one learning seat against seven scripted bots.
readme:
SuperMimic trains a humanoid motion-tracking policy by backpropagating through a learned, differentiable world model.
readme:
It includes a differentiable world model, a goal-conditioned policy, a Manager-Based task
description:
learned differentiable world model + BPTT policy for G1 humanoid motion tracking, on mjlab/MuJoCo Warp
description:
Build RL environments for any domain from real cases that Browser Use agents mine from the web
readme:
Use it to train model weights with Slime and SGLang, or improve an agent's harness, including its prompts, rules, and skills.
readme:
A self-evolving training arena that turns real-world tool ecosystems into stateful, executable environments—and turns those environments into verifiable agent experience.
How a repository gets this Tag
An agent reads the description, the GitHub topics, and the start of the README of each repository. It chooses Tags only from the Tag list in the AwesomeRepos source code. For each Tag, it quotes the text. A code check keeps the Tag only when the quote is in that text. The quote under each repository is that evidence. A Tag does not rank repositories. It does not say that one repository can replace another. To report a wrong Tag, use "Report a problem with this page" on the page of the repository. All numbers on this page count only visible repositories.