README.md

---
license: bsd-3-clause
tags:
- Humanoid-v2
- reinforcement-learning
- Soft Actor Critic
- SRL
- deep-reinforcement-learning
model-index:
- name: SAC
  results:
  - metrics:
    - type: FAS (J=1)
      value: 0.064253 ± 0.00638
      name: FAS
    - type: FAS (J=2)
      value: 0.056522 ± 0.012575
      name: FAS
    - type: FAS (J=4)
      value: 0.080906 ± 0.030329
      name: FAS
    - type: FAS (J=8)
      value: 0.172967 ± 0.022553
      name: FAS
    - type: FAS (J=16)
      value: 0.182832 ± 0.038443
      name: FAS
    task:
      type: OpenAI Gym
      name: OpenAI Gym
    dataset:
      name: Humanoid-v2
      type: Humanoid-v2
  Paper: https://arxiv.org/pdf/2410.08979
  Code: https://github.com/dee0512/Sequence-Reinforcement-Learning

---
# Soft-Actor-Critic: Humanoid-v2

These are 25 trained models over **seeds (0-4)**  and **J = 1, 2, 4, 8, 16** of **Soft actor critic** agent playing **Humanoid-v2** for **[Sequence Reinforcement Learning (SRL)](https://github.com/dee0512/Sequence-Reinforcement-Learning)**.

## Model Sources

**Repository:** [https://github.com/dee0512/Sequence-Reinforcement-Learning](https://github.com/dee0512/Sequence-Reinforcement-Learning)  
**Paper (ICLR):** [https://openreview.net/forum?id=w3iM4WLuvy](https://openreview.net/forum?id=w3iM4WLuvy)  
**Arxiv:** [arxiv.org/pdf/2410.08979](https://arxiv.org/pdf/2410.08979)

# Training Details:
Using the repository:

```
python .\train_sac.py --env_name <env_name> --seed <seed> --j <j>
```

# Evaluation:

Download the models folder and place it in the same directory as the cloned repository. 
Using the repository:

```
python .\eval_sac.py --env_name <env_name> --seed <seed> --j <j>
```

## Metrics:

**FAS:** Frequency Averaged Score  
**j:** Action repetition parameter


# Citation

The paper can be cited with the following bibtex entry:

## BibTeX:

```
@inproceedings{DBLP:conf/iclr/PatelS25,
  author       = {Devdhar Patel and
                  Hava T. Siegelmann},
  title        = {Overcoming Slow Decision Frequencies in Continuous Control: Model-Based
                  Sequence Reinforcement Learning for Model-Free Control},
  booktitle    = {The Thirteenth International Conference on Learning Representations,
                  {ICLR} 2025, Singapore, April 24-28, 2025},
  publisher    = {OpenReview.net},
  year         = {2025},
  url          = {https://openreview.net/forum?id=w3iM4WLuvy}
}
```

## APA:
```
Patel, D., & Siegelmann, H. T. Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control. In The Thirteenth International Conference on Learning Representations.
```