---
license: bsd-3-clause
tags:
- Pendulum-v1
- Reinforcement-Learning
- Decisions
model-index:
- name: TLA
  results:
  - metrics:
    - type: mean_reward
      value: -154.92 +/- 31.97
      name: mean_reward
    - type: action_repetition
      value: 70.32%
      name: action_repetition
    - type: mean_decisions
      value: 62.31
      name: mean_decisions
    task:
      type: reinforcement-learning
      name: reinforcement-learning
    dataset:
      name: Pendulum-v1
      type: Pendulum-v1
---
# Temporally Layered Architecture: Pendulum-v1