Comments (4)
vitchyr
commented on June 20, 2024
Good point. Hmmm, I'm not sure if I want to remove the dependence on MultitaskEnv since that defines the interface. The env_util functions could also be copy/pasted from multiworld, though it seems like a bit redundant.
If you don't want to install multiworld, you can copy/paste the code from here, but otherwise I'm open to suggestions for how else you might fix this.
from rlkit.
dwiel
commented on June 20, 2024
Yeah that makes sense. Perhaps `multiworld` could be made pip installable
and included in the provided environments? It not so much that I dont want
to install, but that it looks like it's not installed by default in any
environments, and unless I'm mistaken is only installable via `pip install
git+https://github...`
β¦On Tue, Jun 11, 2019, 9:13 PM Vitchyr Pong ***@***.***> wrote:
Good point. Hmmm, I'm not sure if I want to remove the dependence on
MultitaskEnv since that defines the interface. The env_util functions
could also be copy/pasted from multiworld, though it seems like a bit
redundant.
If you don't want to install multiworld, you can copy/paste the code from
here
<https://github.com/vitchyr/multiworld/blob/master/multiworld/core/multitask_env.py>,
but otherwise I'm open to suggestions for how else you might fix this.
β
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#60>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AAAHGZXAZKTKRBVYF4GV6OTP2BETLANCNFSM4HXEP2DQ>
.
from rlkit.
CarloLucibello
commented on June 20, 2024
multiworld is needed to run the DQN example on CartPole as well, which is not ideal:
$ python examples/dqn_and_double_dqn.py
Traceback (most recent call last):
File "examples/dqn_and_double_dqn.py", line 12, in <module>
from rlkit.torch.dqn.dqn import DQNTrainer
File "/home/carlo/Git/rlkit/rlkit/torch/dqn/dqn.py", line 10, in <module>
from rlkit.torch.torch_rl_algorithm import TorchTrainer
File "/home/carlo/Git/rlkit/rlkit/torch/torch_rl_algorithm.py", line 7, in <module>
from rlkit.core.batch_rl_algorithm import BatchRLAlgorithm
File "/home/carlo/Git/rlkit/rlkit/core/batch_rl_algorithm.py", line 4, in <module>
from rlkit.core.rl_algorithm import BaseRLAlgorithm
File "/home/carlo/Git/rlkit/rlkit/core/rl_algorithm.py", line 8, in <module>
from rlkit.samplers.data_collector import DataCollector
File "/home/carlo/Git/rlkit/rlkit/samplers/data_collector/__init__.py", line 6, in <module>
from rlkit.samplers.data_collector.path_collector import (
File "/home/carlo/Git/rlkit/rlkit/samplers/data_collector/path_collector.py", line 3, in <module>
from rlkit.envs.vae_wrapper import VAEWrappedEnv
File "/home/carlo/Git/rlkit/rlkit/envs/vae_wrapper.py", line 11, in <module>
from multiworld.core.multitask_env import MultitaskEnv
ModuleNotFoundError: No module named 'multiworld'
from rlkit.
vitchyr
commented on June 20, 2024
Addressed with 60d1ab8. Thanks for the feedback!
from rlkit.
Related Issues (20)
- unable to create the conda environment with linux-cpu-env.yml HOT 2
- Issue SMAC algorithm HOT 4
- multi-GPU optimised implementations for running algorithms HOT 1
- Doubt on Q-function loss in AWAC HOT 1
- Question about VAEPolicy in rlkit.torch.sac.policies HOT 2
- CustomMDPPathCollector is not found HOT 2
- Doubt on advantage calculation to update the policy on AWAC.
- Position Control with mujoco-py
- Cannot reproduce the results of IQL on antmaze HOT 1
- High Memory & Disk Requirement for SMAC HOT 1
- Skew-fit gaussian_identity_variance
- AWAC doesn't profit from offline data HOT 4
- IQL: make checkpoints public
- Could someone provide right environment installation procedure? HOT 4
- Python3.5 is not suitable for this project! HOT 1
- Why I could not see result fileοΌ
- SAC log_alpha different from paper HOT 1
- IQL results different with the paper HOT 1
- Reproduce and create figures results in AWAC.
- Download link is expired HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. πππ
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from rlkit.