Farama-Foundation / D4RL

A collection of reference environments for offline reinforcement learning
Apache License 2.0
1.35k stars 285 forks source link

Unable to get video using hopper-expert-v2 but was able to get with ant-v2 etc. #218

Open rebecajohn opened 1 year ago

rebecajohn commented 1 year ago

Unable to get video using hopper-expert-v2 but was able to get with ant-v2 etc.

code:

@title test virtual display

@markdown If you see a video of a four-legged ant fumbling about, setup is complete!

import gym import d4rl

from cs285.infrastructure.colab_utils import ( wrap_env, show_video )

env = wrap_env(gym.make("hopper-expert-v2"))

observation = env.reset() for i in range(100): env.render(mode='rgbarray') obs, rew, term, = env.step(env.action_space.sample() ) if term: break;

env.close() print('Loading video...') show_video()

output: warning: Flow failed to import. Set the environment variable D4RL_SUPPRESS_IMPORT_ERROR=1 to suppress this message. No module named 'flow' INFO:absl:MUJOCO_GL is not set, so an OpenGL backend will be chosen automatically. INFO:absl:Failed to import OpenGL backend: glfw INFO:OpenGL.acceleratesupport:No OpenGL_accelerate module loaded: No module named 'OpenGL_accelerate' INFO:absl:Successfully imported OpenGL backend: egl INFO:absl:MuJoCo library version is: 2.3.7 Warning: CARLA failed to import. Set the environment variable D4RL_SUPPRESS_IMPORT_ERROR=1 to suppress this message. No module named 'carla' /usr/local/lib/python3.10/dist-packages/gym/spaces/box.py:78: UserWarning: WARN: Box bound precision lowered by casting to float32 logger.warn(f"Box bound precision lowered by casting to {self.dtype}")

Loading video... Could not find video