# Reinforcement Learning on CartPole Pure

Source: [Reinforcement Learning on CartPole Pure](<https://www.sota2.com/research/sota/reinforcement-learning-on-cartpole-pure>)

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

Data updated: 2026-02-26T05:35:45.072Z

Evaluation of Reinforcement Learning agents on the CartPole Pure environment, measured by average reward across specific configuration settings (e.g., episode length and discount factor combinations).

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 | Reinforcement Learning |
| Dataset (including any stated split) | CartPole Pure |
| Metric | Average Reward (2/0.5) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 30 of 30 |
| 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

- [Average Reward (2/0.5)](<https://www.sota2.com/research/sota/reinforcement-learning-on-cartpole-pure.md?metric=Average%20Reward%20(2%2F0.5)>): Higher is better; unit: SCALAR.

- [Average Reward (10/0.85)](<https://www.sota2.com/research/sota/reinforcement-learning-on-cartpole-pure.md?metric=Average%20Reward%20(10%2F0.85)>): Higher is better; unit: SCALAR.

- [Average Reward (10/0.15)](<https://www.sota2.com/research/sota/reinforcement-learning-on-cartpole-pure.md?metric=Average%20Reward%20(10%2F0.15)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Average Reward (2/0.5) | Result date | Report paper |
| --- | --- | --- | --- |
| True env+MPC | 200 | Not recorded | 68fa6b371e209131cea2cf55 |
| True env+MPC | 200 | Not recorded | 68fa6b371e209131cea2cf55 |
| True env+MPC | 200 | Not recorded | 68fa6b371e209131cea2cf55 |
| PerSim | 199.8 | Not recorded | 68fa6b371e209131cea2cf55 |
| PerSim | 199.7 | Not recorded | 68fa6b371e209131cea2cf55 |
| PerSim | 197.7 | Not recorded | 68fa6b371e209131cea2cf55 |
| Vanilla CaDM | 171.1 | Not recorded | 68fa6b371e209131cea2cf55 |
| Vanilla CaDM | 168 | Not recorded | 68fa6b371e209131cea2cf55 |
| MOREL | 166.7 | Not recorded | 68fa6b371e209131cea2cf55 |
| BCQ | 166.2 | Not recorded | 68fa6b371e209131cea2cf55 |
| CQL | 163.7 | Not recorded | 68fa6b371e209131cea2cf55 |
| CQL | 154.4 | Not recorded | 68fa6b371e209131cea2cf55 |
| Vanilla CaDM | 150.5 | Not recorded | 68fa6b371e209131cea2cf55 |
| CQL | 122.8 | Not recorded | 68fa6b371e209131cea2cf55 |
| BCQ | 98.9 | Not recorded | 68fa6b371e209131cea2cf55 |
| PE-TS CaDM | 98.3 | Not recorded | 68fa6b371e209131cea2cf55 |
| PE-TS CaDM | 92.3 | Not recorded | 68fa6b371e209131cea2cf55 |
| PE-TS CaDM | 88.6 | Not recorded | 68fa6b371e209131cea2cf55 |
| CQL | 67.4 | Not recorded | 68fa6b371e209131cea2cf55 |
| BCQ | 67.3 | Not recorded | 68fa6b371e209131cea2cf55 |
| BCQ | 65.4 | Not recorded | 68fa6b371e209131cea2cf55 |
| MOREL | 50.2 | Not recorded | 68fa6b371e209131cea2cf55 |
| BCQ | 44.8 | Not recorded | 68fa6b371e209131cea2cf55 |
| BCQ | 43.9 | Not recorded | 68fa6b371e209131cea2cf55 |
| CQL | 42.4 | Not recorded | 68fa6b371e209131cea2cf55 |
| MOREL | 41.4 | Not recorded | 68fa6b371e209131cea2cf55 |
| CQL | 39.9 | Not recorded | 68fa6b371e209131cea2cf55 |
| MOREL | 35.8 | Not recorded | 68fa6b371e209131cea2cf55 |
| MOREL | 35.8 | Not recorded | 68fa6b371e209131cea2cf55 |
| MOREL | 33.7 | Not recorded | 68fa6b371e209131cea2cf55 |

### True env+MPC

Average Reward (2/0.5): 200. Result ID: 698e71aaffc3901de09da3cc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Oracle (True Environment)"}. This record does not assert independent reproduction.

### True env+MPC

Average Reward (2/0.5): 200. Result ID: 698e71aaffc3901de09da3ea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Oracle (True Environment)"}. This record does not assert independent reproduction.

### True env+MPC

Average Reward (2/0.5): 200. Result ID: 698e71aaffc3901de09da408.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Oracle (True Environment)"}. This record does not assert independent reproduction.

### PerSim

Average Reward (2/0.5): 199.8. Result ID: 698e71aaffc3901de09da3ff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-20"}. This record does not assert independent reproduction.

### PerSim

Average Reward (2/0.5): 199.7. Result ID: 698e71aaffc3901de09da3c3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Pure"}. This record does not assert independent reproduction.

### PerSim

Average Reward (2/0.5): 197.7. Result ID: 698e71aaffc3901de09da3e1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Random"}. This record does not assert independent reproduction.

### Vanilla CaDM

Average Reward (2/0.5): 171.1. Result ID: 698e71aaffc3901de09da400.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67d31e209131cea18bbc.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-20"}. This record does not assert independent reproduction.

### Vanilla CaDM

Average Reward (2/0.5): 168. Result ID: 698e71aaffc3901de09da3c4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67d31e209131cea18bbc.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Pure"}. This record does not assert independent reproduction.

### MOREL

Average Reward (2/0.5): 166.7. Result ID: 698e71aaffc3901de09da406.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69731e209131cea22286.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-20","Algorithm variant":"Planning"}. This record does not assert independent reproduction.

### BCQ

Average Reward (2/0.5): 166.2. Result ID: 698e71aaffc3901de09da3c6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66391e209131cea0ef4a.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Pure","Algorithm variant":"Planning"}. This record does not assert independent reproduction.

### CQL

Average Reward (2/0.5): 163.7. Result ID: 698e71aaffc3901de09da404.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa682a1e209131cea1a6c2.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-20","Algorithm variant":"Planning"}. This record does not assert independent reproduction.

### CQL

Average Reward (2/0.5): 154.4. Result ID: 698e71aaffc3901de09da3c8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa682a1e209131cea1a6c2.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Pure","Algorithm variant":"Planning"}. This record does not assert independent reproduction.

### Vanilla CaDM

Average Reward (2/0.5): 150.5. Result ID: 698e71aaffc3901de09da3e2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67d31e209131cea18bbc.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Random"}. This record does not assert independent reproduction.

### CQL

Average Reward (2/0.5): 122.8. Result ID: 698e71aaffc3901de09da3c9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa682a1e209131cea1a6c2.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Pure","Algorithm variant":"Acting"}. This record does not assert independent reproduction.

### BCQ

Average Reward (2/0.5): 98.9. Result ID: 698e71aaffc3901de09da402.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66391e209131cea0ef4a.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-20","Algorithm variant":"Planning"}. This record does not assert independent reproduction.

### PE-TS CaDM

Average Reward (2/0.5): 98.3. Result ID: 698e71aaffc3901de09da401.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67d31e209131cea18bbc.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-20"}. This record does not assert independent reproduction.

### PE-TS CaDM

Average Reward (2/0.5): 92.3. Result ID: 698e71aaffc3901de09da3c5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67d31e209131cea18bbc.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Pure"}. This record does not assert independent reproduction.

### PE-TS CaDM

Average Reward (2/0.5): 88.6. Result ID: 698e71aaffc3901de09da3e3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67d31e209131cea18bbc.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Random"}. This record does not assert independent reproduction.

### CQL

Average Reward (2/0.5): 67.4. Result ID: 698e71aaffc3901de09da3e7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa682a1e209131cea1a6c2.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Random","Algorithm variant":"Acting"}. This record does not assert independent reproduction.

### BCQ

Average Reward (2/0.5): 67.3. Result ID: 698e71aaffc3901de09da403.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66391e209131cea0ef4a.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-20","Algorithm variant":"Acting"}. This record does not assert independent reproduction.

### BCQ

Average Reward (2/0.5): 65.4. Result ID: 698e71aaffc3901de09da3c7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66391e209131cea0ef4a.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Pure","Algorithm variant":"Acting"}. This record does not assert independent reproduction.

### MOREL

Average Reward (2/0.5): 50.2. Result ID: 698e71aaffc3901de09da3e8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69731e209131cea22286.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Random","Algorithm variant":"Planning"}. This record does not assert independent reproduction.

### BCQ

Average Reward (2/0.5): 44.8. Result ID: 698e71aaffc3901de09da3e4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66391e209131cea0ef4a.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Random","Algorithm variant":"Planning"}. This record does not assert independent reproduction.

### BCQ

Average Reward (2/0.5): 43.9. Result ID: 698e71aaffc3901de09da3e5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66391e209131cea0ef4a.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Random","Algorithm variant":"Acting"}. This record does not assert independent reproduction.

### CQL

Average Reward (2/0.5): 42.4. Result ID: 698e71aaffc3901de09da405.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa682a1e209131cea1a6c2.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-20","Algorithm variant":"Acting"}. This record does not assert independent reproduction.

### MOREL

Average Reward (2/0.5): 41.4. Result ID: 698e71aaffc3901de09da407.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69731e209131cea22286.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-20","Algorithm variant":"Acting"}. This record does not assert independent reproduction.

### CQL

Average Reward (2/0.5): 39.9. Result ID: 698e71aaffc3901de09da3e6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa682a1e209131cea1a6c2.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Random","Algorithm variant":"Planning"}. This record does not assert independent reproduction.

### MOREL

Average Reward (2/0.5): 35.8. Result ID: 698e71aaffc3901de09da3ca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69731e209131cea22286.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Pure","Algorithm variant":"Planning"}. This record does not assert independent reproduction.

### MOREL

Average Reward (2/0.5): 35.8. Result ID: 698e71aaffc3901de09da3e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69731e209131cea22286.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Random","Algorithm variant":"Acting"}. This record does not assert independent reproduction.

### MOREL

Average Reward (2/0.5): 33.7. Result ID: 698e71aaffc3901de09da3cb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69731e209131cea22286.md>)

Recorded evaluation configuration: {"Data source (optimality)":"Pure","Algorithm variant":"Acting"}. This record does not assert independent reproduction.

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