Template updates
Rho FR3 Duo
rho-fr3-duo · policy template by Microsoft · Franka FR3 Duo · finetune first · 30 Hz. Each version below is fixed once published, newest first.
seq init rho-fr3-duo gives the stable version, seq init rho-fr3-duo@beta the beta, and seq init rho-fr3-duo@v<N> any version below that is not withdrawn. A deployment made from this template names the version it runs in seq policy versions and on its page in the console; seq policy upgrade moves it to the newer stable one.
Performance
No runs yet.
Versions
-
As v3;
policy.pysays, as the README does, how a worker's CPU and memory are billed.Needs sequence-ai 0.56.0 or later to deploy it (
pip install -U sequence-ai); its client runs on 0.56.0 or later with its video encoder (pip install -U "sequence-ai[observe]").- v3's files; only
policy.py's comment on CPU and memory changed: the machine its card sets (an L4's 8 cores and 32 GiB), or what it declares where that is more.
Use v4
# start a policy from this version, then deploy it # my_policy_user: the name you choose seq init rho-fr3-duo@v4 my_policy_user seq deploy my_policy_user # or move a deployment made from this template to it seq policy upgrade my_policy_user --to rho-fr3-duo@v4 # on the robot's machine: this version's client.py and its README pip install -U sequence-ai seq init rho-fr3-duo@v4 my_policy_user
In the console, Deploy deploys this version: the console deploys the stable one.
- v3's files; only
-
As v2; the README says a worker's CPU and memory are billed as the machine its card sets.
Needs sequence-ai 0.56.0 or later to deploy it (
pip install -U sequence-ai); its client runs on 0.56.0 or later with its video encoder (pip install -U "sequence-ai[observe]").- v2's files; only the README's billing of CPU and memory changed: the machine its card sets (an L4's 8 cores and 32 GiB), or what it declares where that is more.
Use v3
# start a policy from this version, then deploy it # my_policy_user: the name you choose seq init rho-fr3-duo@v3 my_policy_user seq deploy my_policy_user # or move a deployment made from this template to it seq policy upgrade my_policy_user --to rho-fr3-duo@v3 # on the robot's machine: this version's client.py and its README pip install -U sequence-ai seq init rho-fr3-duo@v3 my_policy_user
-
Microsoft's Rho for the Franka FR3 Duo as before; the README names the frame both poses are in, as Rho's report does.
Needs sequence-ai 0.56.0 or later to deploy it (
pip install -U sequence-ai); its client runs on 0.56.0 or later with its video encoder (pip install -U "sequence-ai[observe]").- Both poses are in a common world frame centered on the dual-arm mount; which arm comes first is still not stated.
- The weights are the head of the checkpoint's pull request 1, which Microsoft merged into main on 2026-11-06.
Use v2
# start a policy from this version, then deploy it # my_policy_user: the name you choose seq init rho-fr3-duo@v2 my_policy_user seq deploy my_policy_user # or move a deployment made from this template to it seq policy upgrade my_policy_user --to rho-fr3-duo@v2 # on the robot's machine: this version's client.py and its README pip install -U sequence-ai seq init rho-fr3-duo@v2 my_policy_user
-
Microsoft's Rho for the Franka FR3 Duo on an L4: a starting point to finetune on your own task.
Needs sequence-ai 0.56.0 or later to deploy it (
pip install -U sequence-ai); its client runs on 0.56.0 or later with its video encoder (pip install -U "sequence-ai[observe]").Use v1
# start a policy from this version, then deploy it # my_policy_user: the name you choose seq init rho-fr3-duo@v1 my_policy_user seq deploy my_policy_user # or move a deployment made from this template to it seq policy upgrade my_policy_user --to rho-fr3-duo@v1 # on the robot's machine: this version's client.py and its README pip install -U sequence-ai seq init rho-fr3-duo@v1 my_policy_user