# Reinforcement Learning on MountainCar (Pure) Source: [Reinforcement Learning on MountainCar (Pure)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:36:21.724Z Evaluation of Reinforcement Learning agents on the standard Mountain Car environment (Pure configuration), measured by average reward achieved under various step/discount factor settings. 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) | MountainCar (Pure) | | Metric | Avg Reward (gamma=0.01) | | 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 - [Avg Reward (gamma=0.01)](): Higher is better; unit: SCALAR. - [Avg Reward (gamma=0.025)](): Higher is better; unit: SCALAR. - [Avg Reward (gamma=0.035)](): Higher is better; unit: SCALAR. ## Recorded results | Method | Avg Reward (gamma=0.01) | Result date | Report paper | | --- | --- | --- | --- | | CQL | -44.6 | Not recorded | 68fa6b371e209131cea2cf55 | | MOREL | -44.6 | Not recorded | 68fa6b371e209131cea2cf55 | | CQL | -44.7 | Not recorded | 68fa6b371e209131cea2cf55 | | CQL | -44.7 | Not recorded | 68fa6b371e209131cea2cf55 | | MOREL | -44.7 | Not recorded | 68fa6b371e209131cea2cf55 | | BCQ | -44.79 | Not recorded | 68fa6b371e209131cea2cf55 | | MOREL | -46 | Not recorded | 68fa6b371e209131cea2cf55 | | BCQ | -50.01 | Not recorded | 68fa6b371e209131cea2cf55 | | True env+MPC | -53.95 | Not recorded | 68fa6b371e209131cea2cf55 | | True env+MPC | -53.95 | Not recorded | 68fa6b371e209131cea2cf55 | | True env+MPC | -53.95 | Not recorded | 68fa6b371e209131cea2cf55 | | PerSim | -54.2 | Not recorded | 68fa6b371e209131cea2cf55 | | PerSim | -54.6 | Not recorded | 68fa6b371e209131cea2cf55 | | Vanilla CaDM | -55.23 | Not recorded | 68fa6b371e209131cea2cf55 | | Vanilla CaDM | -56.73 | Not recorded | 68fa6b371e209131cea2cf55 | | PerSim | -56.8 | Not recorded | 68fa6b371e209131cea2cf55 | | MOREL | -61.3 | Not recorded | 68fa6b371e209131cea2cf55 | | CQL | -61.4 | Not recorded | 68fa6b371e209131cea2cf55 | | BCQ | -67.6 | Not recorded | 68fa6b371e209131cea2cf55 | | BCQ | -71.21 | Not recorded | 68fa6b371e209131cea2cf55 | | PE-TS CaDM | -74.23 | Not recorded | 68fa6b371e209131cea2cf55 | | CQL | -79.4 | Not recorded | 68fa6b371e209131cea2cf55 | | MOREL | -83.5 | Not recorded | 68fa6b371e209131cea2cf55 | | BCQ | -94.87 | Not recorded | 68fa6b371e209131cea2cf55 | | PE-TS CaDM | -102.3 | Not recorded | 68fa6b371e209131cea2cf55 | | Vanilla CaDM | -106.3 | Not recorded | 68fa6b371e209131cea2cf55 | | PE-TS CaDM | -107.6 | Not recorded | 68fa6b371e209131cea2cf55 | | CQL | -176.1 | Not recorded | 68fa6b371e209131cea2cf55 | | BCQ | -364.5 | Not recorded | 68fa6b371e209131cea2cf55 | | MOREL | -373 | Not recorded | 68fa6b371e209131cea2cf55 | ### CQL Avg Reward (gamma=0.01): -44.6. Result ID: 698e71aaffc3901de09da3bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure","Algorithm variant":"Acting"}. This record does not assert independent reproduction. ### MOREL Avg Reward (gamma=0.01): -44.6. Result ID: 698e71aaffc3901de09da3fd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-20","Algorithm variant":"Acting"}. This record does not assert independent reproduction. ### CQL Avg Reward (gamma=0.01): -44.7. Result ID: 698e71aaffc3901de09da3fb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-20","Algorithm variant":"Acting"}. This record does not assert independent reproduction. ### CQL Avg Reward (gamma=0.01): -44.7. Result ID: 698e71aaffc3901de09da419. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-40","Algorithm variant":"Acting"}. This record does not assert independent reproduction. ### MOREL Avg Reward (gamma=0.01): -44.7. Result ID: 698e71aaffc3901de09da41b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-40","Algorithm variant":"Acting"}. This record does not assert independent reproduction. ### BCQ Avg Reward (gamma=0.01): -44.79. Result ID: 698e71aaffc3901de09da3bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure","Algorithm variant":"Acting"}. This record does not assert independent reproduction. ### MOREL Avg Reward (gamma=0.01): -46. Result ID: 698e71aaffc3901de09da3c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure","Algorithm variant":"Planning"}. This record does not assert independent reproduction. ### BCQ Avg Reward (gamma=0.01): -50.01. Result ID: 698e71aaffc3901de09da416. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-40","Algorithm variant":"Planning"}. This record does not assert independent reproduction. ### True env+MPC Avg Reward (gamma=0.01): -53.95. Result ID: 698e71aaffc3901de09da3c2. [Reporting paper]() Recorded evaluation configuration: {"Data source (optimality)":"Oracle (True Environment)"}. This record does not assert independent reproduction. ### True env+MPC Avg Reward (gamma=0.01): -53.95. Result ID: 698e71aaffc3901de09da3fe. [Reporting paper]() Recorded evaluation configuration: {"Data source (optimality)":"Oracle (True Environment)"}. This record does not assert independent reproduction. ### True env+MPC Avg Reward (gamma=0.01): -53.95. Result ID: 698e71aaffc3901de09da41c. [Reporting paper]() Recorded evaluation configuration: {"Data source (optimality)":"Oracle (True Environment)"}. This record does not assert independent reproduction. ### PerSim Avg Reward (gamma=0.01): -54.2. Result ID: 698e71aaffc3901de09da3f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-20"}. This record does not assert independent reproduction. ### PerSim Avg Reward (gamma=0.01): -54.6. Result ID: 698e71aaffc3901de09da413. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-40"}. This record does not assert independent reproduction. ### Vanilla CaDM Avg Reward (gamma=0.01): -55.23. Result ID: 698e71aaffc3901de09da414. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-40"}. This record does not assert independent reproduction. ### Vanilla CaDM Avg Reward (gamma=0.01): -56.73. Result ID: 698e71aaffc3901de09da3f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-20"}. This record does not assert independent reproduction. ### PerSim Avg Reward (gamma=0.01): -56.8. Result ID: 698e71aaffc3901de09da3b9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure"}. This record does not assert independent reproduction. ### MOREL Avg Reward (gamma=0.01): -61.3. Result ID: 698e71aaffc3901de09da41a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-40","Algorithm variant":"Planning"}. This record does not assert independent reproduction. ### CQL Avg Reward (gamma=0.01): -61.4. Result ID: 698e71aaffc3901de09da418. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-40","Algorithm variant":"Planning"}. This record does not assert independent reproduction. ### BCQ Avg Reward (gamma=0.01): -67.6. Result ID: 698e71aaffc3901de09da3bc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure","Algorithm variant":"Planning"}. This record does not assert independent reproduction. ### BCQ Avg Reward (gamma=0.01): -71.21. Result ID: 698e71aaffc3901de09da3f8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-20","Algorithm variant":"Planning"}. This record does not assert independent reproduction. ### PE-TS CaDM Avg Reward (gamma=0.01): -74.23. Result ID: 698e71aaffc3901de09da3bb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure"}. This record does not assert independent reproduction. ### CQL Avg Reward (gamma=0.01): -79.4. Result ID: 698e71aaffc3901de09da3fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-20","Algorithm variant":"Planning"}. This record does not assert independent reproduction. ### MOREL Avg Reward (gamma=0.01): -83.5. Result ID: 698e71aaffc3901de09da3fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-20","Algorithm variant":"Planning"}. This record does not assert independent reproduction. ### BCQ Avg Reward (gamma=0.01): -94.87. Result ID: 698e71aaffc3901de09da417. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-40","Algorithm variant":"Acting"}. This record does not assert independent reproduction. ### PE-TS CaDM Avg Reward (gamma=0.01): -102.3. Result ID: 698e71aaffc3901de09da415. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-40"}. This record does not assert independent reproduction. ### Vanilla CaDM Avg Reward (gamma=0.01): -106.3. Result ID: 698e71aaffc3901de09da3ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure"}. This record does not assert independent reproduction. ### PE-TS CaDM Avg Reward (gamma=0.01): -107.6. Result ID: 698e71aaffc3901de09da3f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-20"}. This record does not assert independent reproduction. ### CQL Avg Reward (gamma=0.01): -176.1. Result ID: 698e71aaffc3901de09da3be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure","Algorithm variant":"Planning"}. This record does not assert independent reproduction. ### BCQ Avg Reward (gamma=0.01): -364.5. Result ID: 698e71aaffc3901de09da3f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Data source (optimality)":"Pure-8-20","Algorithm variant":"Acting"}. This record does not assert independent reproduction. ### MOREL Avg Reward (gamma=0.01): -373. Result ID: 698e71aaffc3901de09da3c1. [Reporting paper]() [Method origin paper]() 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.