sash-a/hrl_pybullet_envs

Locomotion HRL envs in pybullet

hrl_pybullet_envs's Issues

Uniform random agent not moving in AntGather environment

I tried the example code provided in the README. the agent is not making any move from the initial position it was dropped, except it jitters its body a little.

import hrl_pybullet_envs
import gym
import numpy as np

env = gym.make('AntGatherBulletEnv-v0')
env.render()
ob = env.reset()
tot_rew = 0

for i in range(1000):
  # Take random actions
  ob, rew, done, _ = env.step(np.random.uniform(-1, 1, env.action_space.shape))
  tot_rew += rew

  if done: break

print(f'Achieved total reward of: {tot_rew}')

Example Notebook

Can you please provide a Google Colab notebook showcasing a basic example.

"can't set attribute" when trying to make an environment

I tried to run the example notebook which is in the documentation of the repo, but first I encountered the error Pybulletgym is not defined. after installing pybulletgym again there was the error can't set attribute. here is the screenshot of the code.