Skip to main content

TorchRL Agents

TorchRL Agents is a Python package that provides object-oriented reinforcement learning (RL) agents built on top of PyTorch and TorchRL.

Object-Oriented Design

At the core of this package is the Agent abstract base class, which defines a structured interface for RL agents. The Agent class provides a blueprint that other classes can subclass to implement specific RL algorithms. This design ensures consistency and reusability across different agents.

Key Features of the Agent Class:

  • Abstract Methods: Enforces the implementation of essential functionalities, such as processing batches and defining policies.
  • Serialization: Supports saving and loading agent configurations and weights, enabling easy training and deployment.
  • Modularity: Allows for easy extension and customization by subclassing.

By subclassing the Agent class, you can implement various RL algorithms while adhering to a consistent structure.

Installation

pip install torchrl-agents

Examples

See torchrl-examples for some examples where agents are trained on benchmark environments.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Metadata

Release files for torchrl-agents 0.4.12

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for torchrl-agents 0.4.12
File Size Uploaded
torchrl_agents-0.4.12.tar.gz 45.6 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for torchrl-agents 0.4.12
File Interpreter ABI Platform
torchrl_agents-0.4.12-py3-none-any.whl Python 3 none any Details

Total release size: 59.4 kB

Release files / torchrl_agents-0.4.12.tar.gz

Download URL torchrl_agents-0.4.12.tar.gz
Size 45.6 kB
Tags Source
SHA-256 checksum
How to use checksums
d08dfa4968cd424d371430eeec091955ba2f48f15749da78480961254254da14
BLAKE2b-256 checksum
How to use checksums
0345c85a60457f45d291d95c19d5c1513acf2711f08db64615ed56a8b27d9ced
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.6.8

Release files / torchrl_agents-0.4.12-py3-none-any.whl

Download URL torchrl_agents-0.4.12-py3-none-any.whl
Size 13.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
4bbed4aa21a73b1f352e2cf95d7a8e78f0e441fb287661e83bb6c862a2e0a282
BLAKE2b-256 checksum
How to use checksums
f1063288c4542ece5748e8521c301690700d8d04e4f1000a53ec930a71e69692
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.6.8

Release history Release notifications | RSS feed

This release

0.4.12 This release

2 release files

0.3.9

2 release files

0.3.8

2 release files

0.3.7

2 release files

0.3.6

2 release files

0.3.5

2 release files

0.3.4

2 release files

0.3.3

2 release files

0.3.2

2 release files

0.3.1

2 release files

0.3.0

2 release files

0.2.2

2 release files

0.2.1

2 release files

0.2.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page