Reinforcement Learning - Exercice 3

Secret url: https://codalab.lri.fr/competitions/134?secret_key=669495b4-175b-47fe-9aa4-ce1b50416f14
Organized by vberger - Current server time: Aug. 15, 2018, 2:21 p.m. UTC

Previous

Development
Jan. 29, 2018, 5:37 p.m. UTC

Current

Final
Feb. 4, 2018, 11 p.m. UTC

End

Competition Ends
Never

Reinforcement Learning - Exercice 3

Brought to you by Reinforcement Learning & Information Theory course

This challenge requires you to solve the mountain car problem. You get a -0.1 reward per time-step, and a 50 reward for reaching the top.

This challenge was generated using chalab.

Reinforcement Learning - Exercice 3: Evaluation

The submission will be evaluated using the get_reward.

Reinforcement Learning - Exercice 3: Rules

Submissions must be submitted before the 2018-01-28 23:00:00+00:00. You may submit 5 submissions every day and 10 in total.

Development

Start: Jan. 29, 2018, 5:37 p.m.

Description: Development phase: create agents and submit them or directly; your reward is computed in the development environment.

Final

Start: Feb. 4, 2018, 11 p.m.

Description: Final phase: submissions from the previous phase are automatically cloned and used to compute the final score. The results will be revealed when the organizers make them available.

Competition Ends

Never

You must be logged in to participate in competitions.

Sign In
# Username Score
1 STEPHANE_Multon 992.4500
2 RICHARD_Hugo 988.4500
3 GUILLOT_Antoine2 982.1000