KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#dsh #dsh-plugin #ai-agent #developer-tools #codex #typescript #cli #deepseek-harness #claude-code #ai-agents #mcp #rust

SVR

★ 47 Open GitHub ↗

[NeurIPS 2023] Supported Value Regularization for Offline Reinforcement Learning

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Supported Value Regularization for Offline Reinforcement Learning

Code for NeurIPS 2023 accepted paper: [**Supported Value Regularization for Offline Reinforcement Learning**](https://openreview.net/pdf?id=fze7P9oy6l).

## Environment
Paper results were collected with [MuJoCo 210](https://mujoco.org/) (and [mujoco-py 2.1.2.14](https://github.com/openai/mujoco-py)) in [OpenAI gym 0.23.1](https://github.com/openai/gym) with the [D4RL datasets](https://github.com/Farama-Foundation/D4RL). Networks are trained using [PyTorch 1.11.0](https://github.com/pytorch/pytorch) and [Python 3.7](https://www.python.org/).

## Usage

### Pretrained Models

We have uploaded pretrained behavior models in SVR_bcmodels/ to facilitate experiment reproduction.

You can also pretrain behavior models by running:
```
./run_pretrain.sh
```

### Offline RL

You can train SVR on D4RL datasets by running:
```
./run_experiments.sh
```

### Logging

This codebase uses tensorboard. You can view saved runs with:

```
tensorboard --logdir <run_dir>
```

## Citation

If you find this work useful, please consider citing:
```bibtex
@article{mao2023supported,
  title={Supported value regularization for offline reinforcement learning},
  author={Mao, Yixiu and Zhang, Hongchang and Chen, Chen and Xu, Yi and Ji, Xiangyang},
  journal={Advances in Neural Information Processing Systems},
  volume={36},
  pages={40587--40609},
  year={2023}
}
```

SVR

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README