serl

serl copied to clipboard

AttributeError: utd_ratio

5

when I run `bash run_learner.sh` from "Quick Start with SERL in Sim" sent initial network to actor learner: 0%| | 0/1000000 [00:00

Caiyishuai

Hi, thank you for the great work on this repo! In the `async_cable_route_drq` task, I noticed that the `record_demo.py` script requires a pre-trained classifier `checkpoint_path` to initialize the `BinaryRewardClassifierWrapper`. However,...

TedSYt

Good day! I have been trying to get this repository running and I feel that the use of `MujocoRenderer` is somehow outdated (I followed the instructions and it didn't work...

lvjonok

Hi, We are trying to train SERL for a different set of tasks. We see that the compliance params and action_scale very widely between different tasks in SERL. What do...

priyankamandikal

报错信息:None cannot be `None` when the render_mode is not `human`的解决方法

1

修改requirements.txt文件内 将 gymnasium 改为 gymnasium==0.29.1

hejianxin79

MEMORY EXHAUSTED when running the ‘image observation example’ program on an NVIDIA GeForce RTX 4070 Ti

1

I ran into a problem with insufficient memory when running the image observation example(serl/examples/async_drq_sim/async_drq_sim.py) on my NVIDIA GeForce RTX 4070 Ti.The error is as follows: E1221 16:46:49.290140 30613 pjrt_stream_executor_client.cc:3085] Execution...

WenzheHe

Problem about visualizing mujoco simulation when running:test_gym_env_human.py

11

when i run: python franka_sim/franka_sim/test/test_gym_env_human.py  I am very interested in SERL， but i dont known how to solve this problem. ubuntu20.04, Nvidia 565, cuda12.6, I would be very grateful...

parzivar

This fixes "panda/gripper_pos" type to be compatible with the space.Box shape 1.

jborbik

Implementation of Voxel-based vision for SERL

1

Hi all This is a pull request as mentioned [here](https://github.com/rail-berkeley/serl/issues/51). The goal was to implement voxel-based vision for a box picking task with a UR5 robot arm. ### New implementations:...

nisutte

In robot control, the action sent by the policy could not be executed completely in one step, which breaks mdp principle (more like pomdp). In your paper, the control frequence...

guochaoqun1998