garage icon indicating copy to clipboard operation
garage copied to clipboard

A toolkit for reproducible reinforcement learning research.

Results 108 garage issues
Sort by recently updated
recently updated
newest added

Hi, Thank you for providing the quality code. I have a implementation detail question. 1. Why don't you just call optimizer.step() after meta_objective.backward()? https://github.com/rlworkgroup/garage/blob/f056fb8f6226c83d340c869e0d5312d61acf07f0/src/garage/torch/algos/maml.py#L124-L127

Hi I implemented a customized version of the gym reacher environment - actually using an aditional parameter (cameras) for rendering in multiple camera perspectives. I also wrapped the environment with...

This hopefully fixes #2328

i was trying to make environment with 2 discrete action . but i couldn't find argument for akro.Discrete to change shape to 2 . How can i make environment with...

Hi! I'm currently working to implement a policy trained using SAC in mujoco into a real robot. I'm trying to load the two q-functions but I obtain weird result in...

Apparently, classic control environments in Gym have a different key for render modes in `env.metadata`. In fact: ```python >>> import gym >>> env = gym.make('CartPole-v1') >>> env.metadata {'render_modes': ['human', 'rgb_array'],...

What would be the simplest way to constrain the GaussianLSTMModel [1] to output values only within the interval [0.0 .. 1.0]? [1] https://github.com/rlworkgroup/garage/blob/6461a071f0155712add1b41316003e90c9c77899/src/garage/tf/models/gaussian_lstm_model.py#L16 Many thanks in advance!

This has been frequently requested. We've avoided adding support largely because it's difficult to test, and because for many environments sampling on cpu is more efficient anyways, but there are...

Hi, Is there anyone who could run any Garage example on MacBook pro m1? Thanks in advance.