Comments (4)
RMSprop with default DeepMind parameters is complete garbage. After 5,000,000 frames it raised the average score per episode to only -15 for Pong. For reference, Adam can converge to nearly perfect games (average score of +16) in the same amount of time. Long story short, RMSprop in Keras is either different from what they used, or Adam is just plain better. No more exploration will be done with RMSprop.
EDIT: fix some spelling, grammar, etc.
from playing-mario-with-deep-reinforcement-learning.
Nadam and Adam produce similar results. Nadam seems to take a small amount of extra time. Adam will be used from here on out. Notebooks are searching for a solid learning rate to lock for remaining experiments.
EDIT: Nadam just achieved a high average score of 18.1. Rethinking this with more notebooks
from playing-mario-with-deep-reinforcement-learning.
high learning rates seem to cause an explosion of gradients in the early stages. (i.e. 1e-4, 1e-3, 2e-3, etc.). something stable like 2e-5 might be the best learning rate
from playing-mario-with-deep-reinforcement-learning.
Further experiments confirm that Adam running at 1e-4 produces unstable results. 2e-5 will be in place from here on out.
from playing-mario-with-deep-reinforcement-learning.
Related Issues (20)
- Play Time Limit HOT 4
- Final evaluation over 100 episodes (instead of 30) HOT 1
- render_mode in Agent HOT 1
- Games to Test HOT 1
- Reward Schemes HOT 2
- Negative Reward for terminal flag HOT 2
- Cite Ohio HPC Center HOT 1
- DownsampleEnv metadata HOT 2
- Environment HOT 1
- Training Killed by OS HOT 2
- Inefficient render_mode usage in Agent HOT 1
- Broken Prioritized Experience Replay HOT 1
- No registered env with id: DeepQAgentNoFrameskip-v10 HOT 1
- Training error HOT 5
- Out of memory error during training HOT 2
- Do you have results? HOT 2
- cannot import name 'wrap' from 'nes_py.wrappers' HOT 1
- cannot run "python . -m play -o results/SuperMarioBros-1-4-v0/DeepQAgent/2018-08-18_18-33" HOT 1
- ImportError: cannot import name 'wrap'
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 playing-mario-with-deep-reinforcement-learning.