Border

A reinforcement learning library in Rust.

Border consists of the following crates:

• Core and utility
  • border-core (doc) provides basic traits and functions generic to environments and reinforcmenet learning (RL) agents.
  • border-tensorboard (doc) has TensorboardRecorder struct to write records which can be shown in Tensorboard. It is based on tensorboard-rs.
  • border-mlflow-tracking (doc) support MLflow tracking to log metrices during training via REST API.
  • border-async-trainer (doc) defines some traits and functions for asynchronous training of RL agents by multiple actors, which runs sampling processes in parallel. In each sampling process, an agent interacts with an environment to collect samples to be sent to a shared replay buffer.
• Environment
  • border-py-gym-env (doc) is a wrapper of the Gymnasium environments written in Python.
  • border-atari-env (doc) is a wrapper of atari-env, which is a part of gym-rs.
  • border-minari (doc) is a wrapper of Minari.
• Agent
  • border-tch-agent (doc) includes RL agents based on tch, including Deep Q network (DQN), implicit quantile network (IQN), and soft actor critic (SAC).
  • border-candle-agent (doc) includes RL agents based on candle
  • border-policy-no-backend (doc) includes a policy that is independent of any deep learning backend, such as Torch.

Status

Border is experimental and currently under development. API is unstable.

Examples

There are some example sctipts in border/examples directory. These are tested in Docker containers, speficically the one in aarch64 directory on M2 Macbook air. Some scripts take few days for the training process, tested on Ubuntu22.04 virtual machine in GPUSOROBAN, a computing cloud.

Docker

You can find Docker container scripts for developing these crates in the following repository: https://github.com/taku-y/dev-border.

License