Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Added custom task (pull cube with a hook tool) #641

Open
wants to merge 4 commits into
base: main
Choose a base branch
from

Conversation

Viswesh-N
Copy link

No description provided.


qpos[:, -2:] = 0.04
self.agent.robot.set_qpos(qpos)
self.agent.robot.set_pose(sapien.Pose([-0.615, 0, 0]))
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

why are we initializing the robot here? The scene builder handles that already

tcp_pose=self.agent.tcp.pose.raw_pose,
cube_pose=self.cube.pose.raw_pose,
tool_pose=self.l_shape_tool.pose.raw_pose,
)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Following the setup of other envs (e.g. push cube), can you ensure the ground truth info (tool pose, cube pose) are only provided if the observation is state based

self, obs: Any, action: torch.Tensor, info: Dict
):
max_reward = 13.0 # 10 + 1 + 1 + 1
return self.compute_dense_reward(obs=obs, action=action, info=info) / max_reward
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

have you tested the reward function with PPO? If so can you add an example script to examples/baselines/ppo/examples.sh that works?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants