hub / github.com/PacktPublishing/Hands-On-Reinforcement-Learning-for-Games

github.com/PacktPublishing/Hands-On-Reinforcement-Learning-for-Games @main

Chat with this repo

repository ↗ · DeepWiki ↗ · + Follow

1,013 symbols 3,147 edges 127 files 138 documented · 14% ● updated 6mo ago★ 621 open issues

Browse by type

⨍ Functions 857◇ Types & classes 147↳ Endpoints 9

What it actually does AI analysis from the code graph — generated when you open this

loading…

Core symbols most depended-on inside this repo

↓ 37 filesRunningStat

Chapter08/Chapter_8/TRPO/running_state.py

↓ 27 filesModel

An abstract RL model or a GAIL discriminator.

Chapter13/Chapter_13/obs_tower2/model.py

↓ 22 filesLabeledImage

Chapter13/Chapter_13/obs_tower2/labels.py

↓ 14 filesRollout

A batch of trajectory segments. These segments record what an agent saw, what actions it took, what rewards it received, etc. …

Chapter13/Chapter_13/obs_tower2/rollout.py

↓ 8 filesStateFeatures

Generate the part of state vectors that reflect the observation. This does not include rewards or actions.

Chapter13/Chapter_13/obs_tower2/states.py

↓ 8 filesACModel

An actor-critic model, which produces actions and value predictions on top of the features from a base model.

Chapter13/Chapter_13/obs_tower2/model.py

browse all functions →

Shape

Method 552

Function 305

Class 147

Route 9

Languages

Python99%

TypeScript1%

Modules by API surface

Chapter11/Chapter_11/common/wrappers.py42 symbols

Chapter10/Chapter_10/common/wrappers.py42 symbols

Chapter07/Chapter_7/wrappers.py42 symbols

Chapter13/Chapter_13/obs_tower2/model.py39 symbols

Chapter13/Chapter_13/obs_tower2/util.py37 symbols

Chapter11/Chapter_11/common/replay_buffer.py25 symbols

Chapter10/Chapter_10/common/replay_buffer.py25 symbols

Chapter14/Chapter_14/deepmind.py22 symbols

Chapter13/Chapter_13/obs_tower2/batched_env.py21 symbols

Chapter14/Chapter_14/multiprocessing_env.py20 symbols

Chapter14/Chapter_14/Chapter_14_Imagine_A2C.py19 symbols

Chapter07/Chapter_7/Chapter_7_DDQN_wprority.py19 symbols

For agents

$ claude mcp add Hands-On-Reinforcement-Learning-for-Games \
  -- python -m otcore.mcp_server <graph>

⬇ download graph artifact

github.com/PacktPublishing/Hands-On-Reinforcement-Learning-for-Games @main

Core symbols most depended-on inside this repo

Shape

Languages

Modules by API surface

For agents

Ask about this repo answers extend the page