Downloads · 30 days
0
0% of all-time downloads
fetch-reach-sac-her
hhmm1122/fetch-reach-sac-her
fetch-reach-sac-her is a reinforcement learning model from hhmm1122. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for stable-baselines3.
A Soft Actor-Critic (SAC) agent with Hindsight Experience Replay (HER), trained to solve the MuJoCo FetchReach task: move the gripper to a target position from sparse reward. Used here as a fast pipeline-validation ba…
All-time downloads
49
Public
Repo size
6.1 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.zip6.1 MB · 100%
At a glance
- Task
- Reinforcement Learning
- Library
- stable-baselines3
- Access
- Public
- Created
- Jun 16, 2026
- Updated
- Jun 16, 2026
- SHA
- 260f4e42
Model card
From the Hugging Face model README
SAC + HER on FetchReach-v4
A Soft Actor-Critic (SAC) agent with Hindsight Experience Replay (HER), trained to solve the MuJoCo FetchReach task: move the gripper to a target position from sparse reward. Used here as a fast pipeline-validation baseline before the harder PickAndPlace task.
Results
- Evaluation success rate: 100% (deterministic, 20+ episodes)
- Mean episode reward: ~-1.6 (sparse reward)
- Trained for 25k timesteps (~4 min on CPU)
Usage
import gymnasium as gym, gymnasium_robotics
from stable_baselines3 import SAC
from stable_baselines3.common.buffers import DictReplayBuffer
from huggingface_hub import hf_hub_download
gym.register_envs(gymnasium_robotics)
path = hf_hub_download("hhmm1122/fetch-reach-sac-her", "best_model.zip")
env = gym.make("FetchReach-v4", max_episode_steps=50)
model = SAC.load(path, env=env, custom_objects={
"replay_buffer_class": DictReplayBuffer, "replay_buffer_kwargs": {}, "buffer_size": 1})
Training
- Algorithm: SAC + HER (
n_sampled_goal=4,goal_selection_strategy="future") - Network: MLP [256, 256, 256], batch 256, lr 1e-3, gamma 0.95
- Framework: Stable-Baselines3 2.8.0, Gymnasium-Robotics 1.4.2
Full code: https://github.com/IAmHassanMehmood/rl-fetch-manipulation1~--- library_name: stable-baselines3 tags:
- reinforcement-learning
- robotics
- mujoco
- gymnasium-robotics
- sac
- hindsight-experience-replay model-index:
- name: SAC-HER-FetchReach
results:
- task:
type: reinforcement-learning
dataset:
name: FetchReach-v4
type: FetchReach-v4
metrics:
- type: success_rate value: "100%"
- task:
type: reinforcement-learning
dataset:
name: FetchReach-v4
type: FetchReach-v4
metrics:
SAC + HER on FetchReach-v4
A Soft Actor-Critic (SAC) agent with Hindsight Experience Replay (HER), trained to solve the MuJoCo FetchReach task: move the gripper to a target position from sparse reward. Used here as a fast pipeline-validation baseline before the harder PickAndPlace task.
Results
- Evaluation success rate: 100% (deterministic, 20+ episodes)
- Mean episode reward: ~-1.6 (sparse reward)
- Trained for 25k timesteps (~4 min on CPU)
Usage
import gymnasium as gym, gymnasium_robotics
from stable_baselines3 import SAC
from stable_baselines3.common.buffers import DictReplayBuffer
from huggingface_hub import hf_hub_download
gym.register_envs(gymnasium_robotics)
path = hf_hub_download("hhmm1122/fetch-reach-sac-her", "best_model.zip")
env = gym.make("FetchReach-v4", max_episode_steps=50)
model = SAC.load(path, env=env, custom_objects={
"replay_buffer_class": DictReplayBuffer, "replay_buffer_kwargs": {}, "buffer_size": 1})
Training
- Algorithm: SAC + HER (
n_sampled_goal=4,goal_selection_strategy="future") - Network: MLP [256, 256, 256], batch 256, lr 1e-3, gamma 0.95
- Framework: Stable-Baselines3 2.8.0, Gymnasium-Robotics 1.4.2
Full code: https://github.com/IAmHassanMehmood/rl-fetch-manipulation
- Task
- Reinforcement Learning
- Library
- stable-baselines3
- Created
- Jun 16, 2026
- Updated
- Jun 16, 2026