Comments (6)
Ah yeah, makes sense! Also I copied the new envs into my code and had to add 'max_episode_steps': 1000
to the specs to get the time-limited versions of the environments by default
from mbpo.
Ah, and also this config file points to the Humanoid-v2, so perhaps the mbpo/env
version is being used somewhere?
from mbpo.
Sorry one last question -- the configs for the hopper/walker also point to the gym v2 versions of these environments, which have early termination and alive bonuses. Do you actually use the parameterized v3 environments that don't have early termination or alive bonuses?
from mbpo.
Thanks for the questions!
We're using the v2 environments. The changes in Ant and Humanoid should be limited to truncating the observations, and the termination conditions should be the same as in the originals (Ant, Humanoid for reference).
I just pushed a commit that hopefully makes this clearer from reading the code. It changes the environment registration so that the modified environments have unique names instead of overwriting the defaults, and removes environment parameters that are not actually used because we test on different versions of the environments. (It is a bit unfortunate that those unused parameters were there in the first place; thanks for catching that.)
from mbpo.
Great, thanks for the quick response and clarification! It may be worth making this difference more visible somewhere as the paper says the 1000-step versions of these environments are used but most of these v2 environments use early termination
from mbpo.
We included the sentence about using the standard 1000-step benchmarks because it's common to modify them to have a shorter horizon (eg, here and here), and this caused some of the baselines to look like they had different performance than originally reported. I can see how this is a bit underspecified now that there are newer versions of the environments that always run for 1000 steps, so I'll make note of this in the paper. Thanks for the catch!
from mbpo.
Related Issues (20)
- mujoco-py checkpoint does not exist HOT 1
- Observation of the mujoco env HOT 2
- [question] specifying a custom log directory HOT 2
- ModuleNotFoundError: No module named 'softlearning.utils' HOT 2
- Is there a way to directly run python file
- How do you run examples using python main.py?
- Different constant in the reward function of Humanoid w.r.t the original Humanoid HOT 2
- Algorithm Architecture and Pytorch Implementation HOT 4
- Potential Memory Leak HOT 4
- Pusher_2d.xml does not exist HOT 3
- 'GymAdapter' object has no attribute '_Serializable__initialize' HOT 1
- Cannot run HOT 4
- Question on Lemma B.3 HOT 1
- Environment creation via gpu-env.yml fails HOT 1
- MBPO not solving Continuous mountain car problem. HOT 1
- Viskit Installation Problem HOT 1
- this code is good,and i want to extend experiment not limited to mujoco
- intuition on the loss function
- Runtime error on Walker2D HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 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. 📊📈🎉
-
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 ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from mbpo.