Comments (4)
Identical behavior is not guaranteed across different gymnasium environment versions, in fact that is the point of environment versions, that being said if you want closer performance, you could try using an earlier version of mujoco
library with the Humanoid-v4
or Humanoid-v5
environment
from gymnasium.
@Kallinteris-Andreas Thanks for your prompt reply! I fully acknowledge the guarantee that identical behavior is only guaranteed within the same gymnasium environment version. However, your statement may be a little bit "self-contradictory", that:
a. the environment behavior could change across different underlying mujoco version, but
b. the environment behavior should keep consistent with fixed environment version
Regarding the specific Humanoid environment, I am quite confident that the program logic on the Gymnasium side of V3 and V4 are identical, and only the called API differs. So, I'm pretty sure that Humanoid-V4 would exhibit V3-like behavior with old enough mujoco binding (e.g., 2.1.5), and the environment behavior silently changes as mujoco upgrades.
from gymnasium.
Humanoid version 3 and humanoid version 4 are definitely not identical, They have different reward functions because version 4 contact cost is always 0, (due to a bug)
regarding MuJoCo version differences:
https://gymnasium.farama.org/main/environments/mujoco/#exact-reproducibility
from gymnasium.
Sorry for my negligence and inclarity. The core logic to call mujoco simulation is what I refer to. I noticed the minor contact reward difference. Your point about exact reproducibility is fair enough, though I was not expecting obvious numerical difference since the first step of simulation between V3 and V4 with same seed (maximum absolute difference ~0.75).
from gymnasium.
Related Issues (20)
- [Bug Report] `torch_to_numpy` fails when tensors are not on cpu HOT 1
- [Bug Report] check_step_determinism obscur working HOT 6
- [Bug Report] "TypeError: 'float' object does not support indexing" in step method after 12M steps of training. HOT 2
- [Proposal] Clarify Taxi Environment Starting State in Documentation HOT 1
- Can't run flappy bird envrionment with gymnasium HOT 1
- [Proposal] Allow to specify dtype for Discrete HOT 1
- [To investigate] Check that the new autoreset order works correctly in vectorized jax envs HOT 3
- [Bug] info dictionary in `env.step()` does not include all claimed terms HOT 2
- [Bug Report] The description of the observation space of "half cheetah" is not correct on the documentation website. HOT 1
- [Question] Automated planning over simulators support HOT 4
- ERROR: Failed building wheel for box2d-py HOT 1
- [Bug Report] truncated is commented out HOT 1
- [Bug Report] shallow copy of info and observation after termination HOT 1
- [Bug Report] Error in Env Rendering Due to Current Dependency Installation HOT 1
- [Bug Report] Wrapper type hints seem to be specified incorrectly? HOT 1
- [New feature] Add reset options support for functional jax envs
- [Bug Report] default_camera_config in MujocoEnv seems not working HOT 6
- [Bug Report] LunarLander continuous mode immediately raises exception due to incompatibility between numpy and box2d HOT 1
- [Bug Report] Custom environment documentation example gif missing HOT 2
- [Question] Wiki / Leaderboards?
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 gymnasium.