TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/TLA

TLA

Reported on 24 benchmarks across 1 task · 1 paper · 23 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Playing Games24 results

  • OpenAI GymonHalfCheetah-v2
    Action Repetition· 2023-05-30
    0.1805
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonHalfCheetah-v2
    Average Decisions· 2023-05-30
    831.42
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonHalfCheetah-v2
    Mean Reward· 2023-05-30
    9571.99
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonInvertedDoublePendulum-v2
    Action Repetition· 2023-05-30
    0.7522
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonInvertedDoublePendulum-v2
    Average Decisions· 2023-05-30
    247.76
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonInvertedDoublePendulum-v2
    Mean Reward· 2023-05-30
    9356.67
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonPendulum-v1
    Action Repetition· 2023-05-30
    0.7032
    best: 0.8073 (TLA with Hierarchical Reward Functions)
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonPendulum-v1
    Average Decisions· 2023-05-30
    62.31
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonPendulum-v1
    Mean Reward· 2023-05-30
    -154.92
    best: -125.02 (TLA with Hierarchical Reward Functions)
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonAnt-v2
    Action Repetition· 2023-05-30
    0.1268
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonAnt-v2
    Average Decisions· 2023-05-30
    860.21
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonAnt-v2
    Mean Reward· 2023-05-30
    5163.54
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonWalker2d-v2
    Action Repetition· 2023-05-30
    0.4745
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonWalker2d-v2
    Average Decisions· 2023-05-30
    513.12
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonHopper-v2
    Action Repetition· 2023-05-30
    0.5722
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonHopper-v2
    Average Decisions· 2023-05-30
    423.91
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonHopper-v2
    Mean Reward· 2023-05-30
    3458.22
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonMountainCarContinuous-v0
    Action Repetition· 2023-05-30
    0.914
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonMountainCarContinuous-v0
    Average Decisions· 2023-05-30
    10.6
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonMountainCarContinuous-v0
    Mean Reward· 2023-05-30
    93.88
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonInvertedPendulum-v2
    Action Repetition· 2023-05-30
    0.8882
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonInvertedPendulum-v2
    Average Decisions· 2023-05-30
    111.79
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonInvertedPendulum-v2
    Mean Reward· 2023-05-30
    1000
    SOTA
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701
  • OpenAI GymonWalker2d-v2
    Mean Reward· 2023-05-30
    3878.41
    best: 5813 (AWR)
    Optimizing Attention and Cognitive Control Costs Using Temporally-Layered ArchitecturesarXiv:2305.18701