faridamoukhtar
/

CarRacing_v3_TD3

Reinforcement Learning

deep-reinforcement-learning

custom-implementation

Eval Results (legacy)

Model card Files Files and versions

TD3 Agent for CarRacing-v3

Trained TD3 agent playing CarRacing-v3.

Results

Mean reward: -92.98
Std reward: 0.83
Evaluated over 100 episodes

Downloads last month: 1

Video Preview

Reinforcement Learning

loading

Evaluation results

mean_reward on CarRacing-v3
self-reported

-92.98 +/- 0.83