# Classic Discrete Control on CartPole v1

Source: [Classic Discrete Control on CartPole v1](<https://www.sota2.com/research/sota/classic-discrete-control-on-cartpole-v1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-29T07:39:01.772Z

Evaluation of algorithms on the CartPole v1 environment focusing on classic discrete control performance, measured by Mean Episodic Return.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Classic Discrete Control |
| Dataset (including any stated split) | CartPole v1 |
| Metric | Mean Episodic Return |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Mean Episodic Return](<https://www.sota2.com/research/sota/classic-discrete-control-on-cartpole-v1.md?metric=Mean%20Episodic%20Return>): Higher is better; unit: SCALAR.

- [FP16 Usage (%)](<https://www.sota2.com/research/sota/classic-discrete-control-on-cartpole-v1.md?metric=FP16%20Usage%20(%25)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Mean Episodic Return | Result date | Report paper |
| --- | --- | --- | --- |
| FP16-PPO | 495 | Not recorded | 69f03f7455a3c32af89fa4c2 |
| INT8-PPO | 492 | Not recorded | 69f03f7455a3c32af89fa4c2 |
| MLP-PPO | 489 | Not recorded | 69f03f7455a3c32af89fa4c2 |
| INT4-PPO | 487 | Not recorded | 69f03f7455a3c32af89fa4c2 |
| BitRL-1bit | 476 | Not recorded | 69f03f7455a3c32af89fa4c2 |
| FedQHD | 466.3 | Not recorded | 6a191d9ddbd7150506f82801 |
| Oracle QHD† | 458.5 | Not recorded | 6a191d9ddbd7150506f82801 |
| Oracle QHD† | 373.2 | Not recorded | 6a191d9ddbd7150506f82801 |
| FedQHD | 351.1 | Not recorded | 6a191d9ddbd7150506f82801 |
| Trunc. FedAvg-QHD | 230.8 | Not recorded | 6a191d9ddbd7150506f82801 |
| Oracle DQN† | 204.4 | Not recorded | 6a191d9ddbd7150506f82801 |
| Distill. FedDQN | 169.9 | Not recorded | 6a191d9ddbd7150506f82801 |
| Distill. FedDQN | 149.4 | Not recorded | 6a191d9ddbd7150506f82801 |
| Oracle DQN† | 139.1 | Not recorded | 6a191d9ddbd7150506f82801 |
| FedAvg-DQN | 120.8 | Not recorded | 6a191d9ddbd7150506f82801 |
| Trunc. FedAvg-QHD | 112.6 | Not recorded | 6a191d9ddbd7150506f82801 |
| Indep. QHD | 26.1 | Not recorded | 6a191d9ddbd7150506f82801 |
| Indep. QHD | 24 | Not recorded | 6a191d9ddbd7150506f82801 |

### FP16-PPO

Mean Episodic Return: 495. Result ID: 69f0875347f34ce924d70ac2.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7455a3c32af89fa4c2.md>)

Recorded evaluation configuration: {"Precision":"FP16"}. This record does not assert independent reproduction.

### INT8-PPO

Mean Episodic Return: 492. Result ID: 69f0875347f34ce924d70ac3.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7455a3c32af89fa4c2.md>)

Recorded evaluation configuration: {"Precision":"INT8"}. This record does not assert independent reproduction.

### MLP-PPO

Mean Episodic Return: 489. Result ID: 69f0875347f34ce924d70ac6.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7455a3c32af89fa4c2.md>)

Recorded evaluation configuration: {"Architecture":"MLP"}. This record does not assert independent reproduction.

### INT4-PPO

Mean Episodic Return: 487. Result ID: 69f0875347f34ce924d70ac4.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7455a3c32af89fa4c2.md>)

Recorded evaluation configuration: {"Precision":"INT4"}. This record does not assert independent reproduction.

### BitRL-1bit

Mean Episodic Return: 476. Result ID: 69f0875347f34ce924d70ac5.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f7455a3c32af89fa4c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f03f7455a3c32af89fa4c2.md>)

Recorded evaluation configuration: {"Precision":"1-bit"}. This record does not assert independent reproduction.

### FedQHD

Mean Episodic Return: 466.3. Result ID: 6a19428bfbc373592c1350ba.

[Reporting paper](<https://www.sota2.com/research/paper/6a191d9ddbd7150506f82801.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a191d9ddbd7150506f82801.md>)

Recorded evaluation configuration: {"Encoder Setting":"Homo"}. This record does not assert independent reproduction.

### Oracle QHD†

Mean Episodic Return: 458.5. Result ID: 6a19428bfbc373592c1350bd.

[Reporting paper](<https://www.sota2.com/research/paper/6a191d9ddbd7150506f82801.md>)

Recorded evaluation configuration: {"Encoder Setting":"Hetero"}. This record does not assert independent reproduction.

### Oracle QHD†

Mean Episodic Return: 373.2. Result ID: 6a19428bfbc373592c1350bc.

[Reporting paper](<https://www.sota2.com/research/paper/6a191d9ddbd7150506f82801.md>)

Recorded evaluation configuration: {"Encoder Setting":"Homo"}. This record does not assert independent reproduction.

### FedQHD

Mean Episodic Return: 351.1. Result ID: 6a19428bfbc373592c1350bb.

[Reporting paper](<https://www.sota2.com/research/paper/6a191d9ddbd7150506f82801.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a191d9ddbd7150506f82801.md>)

Recorded evaluation configuration: {"Encoder Setting":"Hetero"}. This record does not assert independent reproduction.

### Trunc. FedAvg-QHD

Mean Episodic Return: 230.8. Result ID: 6a19428bfbc373592c1350b5.

[Reporting paper](<https://www.sota2.com/research/paper/6a191d9ddbd7150506f82801.md>)

Recorded evaluation configuration: {"Encoder Setting":"Homo"}. This record does not assert independent reproduction.

### Oracle DQN†

Mean Episodic Return: 204.4. Result ID: 6a19428bfbc373592c1350bf.

[Reporting paper](<https://www.sota2.com/research/paper/6a191d9ddbd7150506f82801.md>)

Recorded evaluation configuration: {"Encoder Setting":"Hetero"}. This record does not assert independent reproduction.

### Distill. FedDQN

Mean Episodic Return: 169.9. Result ID: 6a19428bfbc373592c1350b8.

[Reporting paper](<https://www.sota2.com/research/paper/6a191d9ddbd7150506f82801.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76d71e209131cea6f7a4.md>)

Recorded evaluation configuration: {"Encoder Setting":"Homo"}. This record does not assert independent reproduction.

### Distill. FedDQN

Mean Episodic Return: 149.4. Result ID: 6a19428bfbc373592c1350b9.

[Reporting paper](<https://www.sota2.com/research/paper/6a191d9ddbd7150506f82801.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76d71e209131cea6f7a4.md>)

Recorded evaluation configuration: {"Encoder Setting":"Hetero"}. This record does not assert independent reproduction.

### Oracle DQN†

Mean Episodic Return: 139.1. Result ID: 6a19428bfbc373592c1350be.

[Reporting paper](<https://www.sota2.com/research/paper/6a191d9ddbd7150506f82801.md>)

Recorded evaluation configuration: {"Encoder Setting":"Homo"}. This record does not assert independent reproduction.

### FedAvg-DQN

Mean Episodic Return: 120.8. Result ID: 6a19428bfbc373592c1350b7.

[Reporting paper](<https://www.sota2.com/research/paper/6a191d9ddbd7150506f82801.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c2d1e209131cea32921.md>)

Recorded evaluation configuration: {"Encoder Setting":"Homo"}. This record does not assert independent reproduction.

### Trunc. FedAvg-QHD

Mean Episodic Return: 112.6. Result ID: 6a19428bfbc373592c1350b6.

[Reporting paper](<https://www.sota2.com/research/paper/6a191d9ddbd7150506f82801.md>)

Recorded evaluation configuration: {"Encoder Setting":"Hetero"}. This record does not assert independent reproduction.

### Indep. QHD

Mean Episodic Return: 26.1. Result ID: 6a19428bfbc373592c1350b3.

[Reporting paper](<https://www.sota2.com/research/paper/6a191d9ddbd7150506f82801.md>)

Recorded evaluation configuration: {"Encoder Setting":"Homo"}. This record does not assert independent reproduction.

### Indep. QHD

Mean Episodic Return: 24. Result ID: 6a19428bfbc373592c1350b4.

[Reporting paper](<https://www.sota2.com/research/paper/6a191d9ddbd7150506f82801.md>)

Recorded evaluation configuration: {"Encoder Setting":"Hetero"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
