Federico
Federico
I solved it by upgrading to torch 1.8.1
@YadiraF any help would be very much appreciated
Usually I keep all the trackers deactivate by default, including the essential ones because some of them end up being not so essential. So when some website or app it's...
So from what I gathered (please correct me if I am mistaken, I probably am :) ) `Box` defines a continuous action space, but then when you call `sample()` the...
Something like ``` from scipy.stats import truncnorm class CheatingBox(gym.spaces.Box): def __init__(self, low, high, shape=None, dtype=np.float32): super().__init__(low=low, high=high, shape=shape, dtype=dtype) def sample(self): return truncnorm.rvs(self.low, self.high, size=18) ```
Would this be a correct implementation of an half gaussian distribution? Honestly I just reverse-engineered the `DiagonalGaussianDistribution` class and changed `proba_distribution` and `mode`, so I am not sure whether it...
I see, thanks! I did the same but I found that some of that were a bit different so I wanted to double check. What about the joint limits? Did...
Sorry, I meant the max forces/effort applicable to each joint and the term kp for the PID controller when I said joint limits. Are they related in some way to...
Thanks! I will try to take a look. So right now what's the criterion for `done`?