mirror of https://github.com/huggingface/candle.git synced 2025-06-16 10:38:54 +00:00

Files

Laurent Mazare ad73e93da2 Detach the tensors on batch-norm eval. (#1702 )

* Detach the tensors on batch-norm eval.

* Fix pyo3 bindings.

* Black tweak.

* Formatting.

* Also update the pyo3-onnx formatting.

* Apply black.

2024-02-13 14:26:32 +01:00

atari_wrappers.py

Fix a couple typos (#1451 )

2023-12-17 05:20:05 -06:00

ddpg.rs

Detach the tensors on batch-norm eval. (#1702 )

2024-02-13 14:26:32 +01:00

gym_env.rs

Add DDPG and fix Gym wrapper (#1207 )

2023-10-28 19:53:34 +01:00

main.rs

Add Policy Gradient to Reinforcement Learning examples (#1500 )

2023-12-30 09:01:29 +01:00

policy_gradient.rs

Detach the tensors on batch-norm eval. (#1702 )

2024-02-13 14:26:32 +01:00

README.md

Add Policy Gradient to Reinforcement Learning examples (#1500 )

2023-12-30 09:01:29 +01:00

vec_gym_env.rs

Add some reinforcement learning example. (#1090 )

2023-10-14 16:46:43 +01:00

README.md

candle-reinforcement-learning

Reinforcement Learning examples for candle.

This has been tested with gymnasium version 0.29.1. You can install the Python package with:

pip install "gymnasium[accept-rom-license]"

In order to run the examples, use the following commands. Note the additional --package flag to ensure that there is no conflict with the candle-pyo3 crate.

For the Policy Gradient example:

cargo run --example reinforcement-learning --features=pyo3 --package candle-examples -- pg

For the Deep Deterministic Policy Gradient example:

cargo run --example reinforcement-learning --features=pyo3 --package candle-examples -- ddpg