Comments (3)
Also, for the JAX Full Rainbow agent (which has Noisy Nets), and when using Noisy Nets, epsilon greedy is disabled (as in paper snippet above, as well as some other implementations like Kaixhin Rainbow here and here). However, I still see the epsilon_train
set to 0.01 in JAX Full Rainbow (here) and if Noisy is true, the identity_epsilon
function is called which just returns the epsilon value (but doesn't uses 0).
from dopamine.
thank you for pointing this out! this has been fixed here: ed92c57
from dopamine.
Thanks! As for
Is there a Is there a discrepancy here (Rainbow should anneal within 62k steps and not 250k steps), or am I misunderstanding something (or perhaps it really doesn't matter?)
Should the epsilon_decay_period
value for TF Rainbow (which does not use Noisy Nets) be 250k frames as in the Rainbow paper (which makes it 62500 steps with frame_skip=4) or 250k steps (as in current implementation) or perhaps it does not matter)? I have rarely seen a value as low as 62500 steps for epsilon decay, for example RLlib also uses 200k for its DQN variant and epislon greedy exploration is off when using Noisy Nets.
from dopamine.
Related Issues (20)
- “python_requires” should be set with “>=3.5”, as dopamine-rl 4.0.2 is not compatible with all Python versions. HOT 1
- ImportError: cannot import name 'isin' from 'jax._src.numpy.lax_numpy'
- ModuleNotFoundError: No module named 'dopamine.metrics' HOT 5
- Poor introduction to dopamine HOT 2
- DEPRECATION WARNING: Logger is being deprecated. Please switch to CollectorDispatcher! HOT 4
- the return value of step function in atari HOT 7
- Jax agents not passing required argument to replay buffer constructor HOT 2
- Support for farama gymnasium HOT 1
- Load baseline Data HOT 2
- Colab demo for jax agents not working. Error: "no attribute 'online_network'" HOT 1
- Import Error: No file or module"text_summary"
- Score normalization in ReDo HOT 2
- Is it possible to release the evaluation scores of the baseline agents?
- AttributeError: module 'jax.interpreters.xla' has no attribute 'DeviceArray' HOT 6
- Cartpole example is not working in colab.
- Bug for truncated episodes in replaybuffer
- TypeError, 'Regexp cannot be negated' in ReDo when running sac_train_eval.py HOT 2
- [Bug] Issues when running continuous domain example
- Multiple CPUs HOT 1
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 dopamine.