dopamine-rl
Dopamine: A framework for flexible Reinforcement Learning research
Decision gist · record as of 2026-08-14
Yes, if you are conducting RL research or learning algorithm implementation. The framework is actively maintained, carries no known vulnerabilities, and provides a curated set of proven agents with clear code. The 19 dependencies and environment setup overhead make it less suitable for lightweight production inference, but ideal for experimentation and reproducible research.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires manual setup of Atari (ale-py) or Mujoco environments before training; TensorFlow and JAX dependencies have their own system-level prerequisites.
- Low install friction with a pure-Python wheel, but carries 19 runtime dependencies including TensorFlow, JAX, and environment simulators (Gym, Gymnasium, ALE).
- Installation from source is recommended over pip for research use.
License · maintenance · safety
Apache 2.0 (permissive) — Apache 2.0 permissive license allows free use, modification, and distribution in both open and closed projects without copyleft obligations.
last release 2024-10-31 (652 days) · last repo commit 2026-03-24 · 10,894 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 98,516 downloads/mo, #13,077 on PyPI
Alternatives
Verify before relying
pip install dopamine-rl
import dopamine
from dopamine.agents import dqn_agent
# Configure and train an agent on Atari environments- Current Python version support beyond the listed 3.5–3.8 classifiers (requires_python states >=3.5,<4)
- Whether all 19 dependencies are required for basic usage or if subsets suffice for specific agents
- Performance or stability differences between JAX and legacy TensorFlow implementations
What it is and what it does
Dopamine is a research-focused reinforcement learning framework maintained by Google that prioritizes ease of experimentation and code clarity over feature breadth. It implements six well-tested RL agents (DQN, C51, Rainbow, IQN, SAC, PPO) with active development in JAX and legacy support for TensorFlow, designed for researchers and students to prototype new ideas on Atari and Mujoco environments.
The framework emphasizes reproducibility and follows best practices from the RL literature. It ships with 19 dependencies spanning deep learning (TensorFlow, JAX, Flax), environment simulation (Gym, Gymnasium, ALE), and data handling (NumPy, Pandas, OpenCV). Installation from source is recommended for research work because the codebase is designed to be modified directly; pip installation is supported but less typical for active development.
Use it for
- Prototype and test new RL algorithm ideas on Atari benchmark environments with minimal boilerplate.
- Train and compare standard agents (DQN, Rainbow, PPO) to establish baselines for research papers.
- Learn RL algorithm implementation by reading and modifying well-documented, battle-tested agent code.
- Reproduce published results using Dopamine's implementations following Machado et al. (2018) evaluation protocols.
- Extend existing agents with custom reward shaping or network architectures for domain-specific tasks.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are conducting RL research or learning algorithm implementation.
The framework is actively maintained, carries no known vulnerabilities, and provides a curated set of proven agents with clear code. The 19 dependencies and environment setup overhead make it less suitable for lightweight production inference, but ideal for experimentation and reproducible research.
Install
dopamine-rl on PyPI
Before you install
Low install friction with a pure-Python wheel, but carries 19 runtime dependencies including TensorFlow, JAX, and environment simulators (Gym, Gymnasium, ALE). Installation from source is recommended over pip for research use.
Requires manual setup of Atari (ale-py) or Mujoco environments before training; TensorFlow and JAX dependencies have their own system-level prerequisites.
License in practice
Apache 2.0 permissive license allows free use, modification, and distribution in both open and closed projects without copyleft obligations.
Quickstart
pip install dopamine-rl
import dopamine
from dopamine.agents import dqn_agent
# Configure and train an agent on Atari environmentsVerify before relying
- Current Python version support beyond the listed 3.5–3.8 classifiers (requires_python states >=3.5,<4)
- Whether all 19 dependencies are required for basic usage or if subsets suffice for specific agents
- Performance or stability differences between JAX and legacy TensorFlow implementations
Package facts
| License | Apache 2.0 permissive |
| Python support | Supports the current Python release <4,>=3.5 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 19 packagestensorflowgin-configabsl-pyale-pyopencv-pythongymgymnasiumflaxjaxjaxlibPillownumpypygamepandaspython-snappytf-slimtensorflow-probabilitytf-kerastqdm |
| Maintenance | Actively maintained 652 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 98,516 / month, #13,077 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersIntended Audience :: EducationIntended Audience :: Science/ResearchLicense :: OSI Approved :: Apache Software LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.5Programming Language :: Python :: 3.6Programming Language :: Python :: 3.7Programming Language :: Python :: 3.8Topic :: Scientific/EngineeringTopic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Scientific/Engineering :: MathematicsTopic :: Software DevelopmentTopic :: Software Development :: LibrariesTopic :: Software Development :: Libraries :: Python Modules |
Evidence: dopamine_rl-4.1.2-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “reinforcement learning framework”
- dopamine-rlDopamine is a research framework for prototyping reinforcement…
- mjlabmjlab provides a GPU-accelerated reinforcement learning and robotics…
- open-spielOpenSpiel provides game environments and reinforcement learning…
Give your agent the search over MCP, or paste the wish link into any chat.
More Software Development packages
Provides backported and experimental type hints for Python 3.9+, allowing use of newer typing features on older Python versions and enabling early experimentation with type system PEPs before they enter the standard library.
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Distlib provides low-level packaging utilities for building, distributing, and managing Python software—including metadata handling, version specifiers, wheel support, script installation, and dependency resolution.
See also tianshou · sb3-contrib · rsl-rl-lib · stable-baselines3 · skrl · verl · gymnasium · google-tunix · mjlab · agentlightning