- Mean value is taken over 1,000 episodes
- Error bars indicate standard error
- Environment is continuing
- Execution is stopped after Horizon=k actions
- Discount factor = 0.5, discount horizon = 0.01
 |
| Horizon 10 without error bars |
 |
| Horizon 10 with error bars |
 |
| Horizon 2 without error bars |
 |
| Horizon 2 with error bars |
No comments:
Post a Comment