metadata
tags:
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
- Pyramids
model-index:
- name: Pyramids
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pyramids
type: Pyramids
metrics:
- type: mean_reward
value: '-50.0 +/- 1.00'
name: mean_reward