RL-Adventure
RL-Adventure-2
RL-Adventure | RL-Adventure-2 | |
---|---|---|
3 | 3 | |
2,950 | 3,211 | |
- | - | |
0.0 | 0.0 | |
over 2 years ago | 5 months ago | |
Jupyter Notebook | Jupyter Notebook | |
- | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
RL-Adventure
-
Applied resources in Pytorch?
can check this out.
-
Is there a consensus about RL frameworks?
For me, nothing beats RL-Adventure. It's not perfect, it has bugs, but it's super readable and will let you level up through the different main methods.
-
[N] 20 hours of new lectures on Deep Learning and Reinforcement Learning with lots of examples
Lecture 7: Function approximation. (slides, code, video)
RL-Adventure-2
-
Why does this implementation uniformly initialize the final layer off their network
I am following this implementation of ddpg and found this code -
-
RuntimeError: Trying to backward through the graph a second time (or directly access saved tensors after they have already been freed)
Also, modified this code - https://github.com/higgsfield/RL-Adventure-2/blob/master/1.actor-critic.ipynb
-
[N] 20 hours of new lectures on Deep Learning and Reinforcement Learning with lots of examples
Lecture 8: Policy gradient methods. (slides, code, theory, video)
What are some alternatives?
stable-baselines3 - PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
flux-beamer - Flux is a modern style beamer presentation.
machin - Reinforcement learning library(framework) designed for PyTorch, implements DQN, DDPG, A2C, PPO, SAC, MADDPG, A3C, APEX, IMPALA ...
DeepReinforcementLearningInAction - Code from the Deep Reinforcement Learning in Action book from Manning, Inc
dcss-ai-wrapper - An API for Dungeon Crawl Stone Soup for Artificial Intelligence research.
implementation-matters
nle - The NetHack Learning Environment
acme - A library of reinforcement learning components and agents
maze - Maze Applied Reinforcement Learning Framework
pfrl - PFRL: a PyTorch-based deep reinforcement learning library