OpenAI Gym on HalfCheetah-v4

Metric: Average Return (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Average Return▼	Extra Data	Paper	Date↕	Code
1	SAC	15836.04	No	Soft Actor-Critic: Off-Policy Maximum Entropy De...	2018-01-04	Code
2	DDPG	14934.86	No	Continuous control with deep reinforcement learn...	2015-09-09	Code
3	TD3	12026.73	No	Addressing Function Approximation Error in Actor...	2018-02-26	Code
4	MEow	10981.47	No	Maximum Entropy Reinforcement Learning via Energ...	2024-05-22	Code
5	PPO	6006.11	No	Proximal Policy Optimization Algorithms	2017-07-20	Code

#1SACSOTA
15836.04
Average Return· 2018-01-04
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor Code
#2DDPGSOTA
14934.86
Average Return· 2015-09-09
Continuous control with deep reinforcement learning Code
#3TD3
12026.73
Average Return· 2018-02-26
Addressing Function Approximation Error in Actor-Critic Methods Code
#4MEow
10981.47
Average Return· 2024-05-22
Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow Code
#5PPO
6006.11
Average Return· 2017-07-20
Proximal Policy Optimization Algorithms Code