Minghuan Liu
Minghuan Liu
Hi, Tianhong, thanks for sharing the code. I've tried to run your code based on the guidance in readme ``` mpirun -np 8 python -u train.py --env-name='FetchPush-v1' 2>&1 | tee...
hi, authors. Very appreciate the public code for your nice paper! I want to know if you can share your expert model since the paper does not mention the expert...
## Motivation DMC experiments always need a framestack wrapper. However it is hard to implement it out of envpool because we should wrap env before creating vector envs. ## Solution...
Do some package have something build in your own system? Like a building error showing your path.
The setting are strictly follows your guide and the system is ubuntu16.04. The errors are as follows: (rllab3) xxx@XXX:~/ngsim_env/scripts/imitation$ python validate.py --n_proc 1 --exp_dir ../../data/experiments/NGSIM-gail/ --params_filename itr_1000.npz --random_seed 42 50...
I find that the expert dataset has some problems. For example, for game 'asterix', I use terminal to split the trajectory, and the maximum return is only round 260. Can...
Like the gradient error in DDPG, when you update the actor gradient of agent i, you should pass the output of its policy network into its Q network instead of...
 In your code here uses \pi(s_i) instead of a_i.
When I use: `gym.make("Unimal-v0", agent_name="floor-1409-1-13-01-12-18-30")`, it says: ``` Traceback (most recent call last): File "", line 1, in File "/home/miniconda3/lib/python3.9/site-packages/gym/envs/registration.py", line 676, in make return registry.make(id, **kwargs) File "/home/miniconda3/lib/python3.9/site-packages/gym/envs/registration.py", line...