godot_rl_agents
popgym
godot_rl_agents | popgym | |
---|---|---|
5 | 4 | |
748 | 145 | |
- | 6.3% | |
9.1 | 6.1 | |
22 days ago | about 1 month ago | |
Python | Python | |
MIT License | MIT License |
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.
godot_rl_agents
-
TransformerXL + PPO Baseline + MemoryGym
Thanks! It really depends on the task that you want to implement. But in general, sticking to the standard gymnasium API is important. If you want to implement a 2D environment then PyGame is promising. If it's more like a game, check out Unity ML-Agents or Godot RL Agents. Anything simpler can also be just pure python code. You also need to carefully design your observation space, action space and reward function. My advice is to explore design choices of related environments.
-
An orb learns to dodge obstacles, collect other orbs and reach the end platform by itself using PPO RL AI
1. You will need to setup a virtual environment in python, install the module with pip, and run the "gdrl" command. Then to use it with godot, simply add a "sync" node provided with the plugin to the tree and it will take care of all your agents and their communication with the python module. The agent needs to be in the "AGENT" group and have 3 compulsory variables and some compulsory functions. You can check it out here: Custom Environment .
-
Godot Engine Release Management: 4.0 and beyond
I really want to play with Godot RL Agents but I want to do vision based learning and that’s a bit down their road map. If anyone wants to contribute to add that feature I’d love you!
https://github.com/edbeeching/godot_rl_agents
-
Build custom 3D gridworld environments
Check out Godot RL Agents as an alternative to Unity.
-
[P] Introducing Godot RL Agents
We are proud to announce the release v0.1 of the Godot RL Agents framework, a Deep Reinforcement Learning interface for the Godot Game Engine.
popgym
-
What RL library supports custom LSTM and Transformer neural networks to use with algorithms such as PPO?
POPGym is based on RLlib and has two linear transformers and five or six RNN variants, including LSTM. I've found that transformers tend to perform pretty poorly in RL when compared to RNNs.
-
POPGym: Partially Observable Reinforcement Learning
Code: https://github.com/proroklab/popgym
-
TransformerXL + PPO Baseline + MemoryGym
Have you seen this other ICLR paper, POPGym? Paper: https://openreview.net/forum?id=chDrutUTs0K Code: https://github.com/smorad/popgym
-
Partially observable Continuous Control Gym Environment
https://github.com/smorad/popgym contains 15 partially observable gym environments, but they use discrete actino spaces. I've verified that memoryless models (e.g. PPO+MLP) cannot solve these tasks, except for the navigation ones.
What are some alternatives?
stable-baselines3 - PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
recurrent-ppo-truncated-bptt - Baseline implementation of recurrent PPO using truncated BPTT
Miniworld - Simple and easily configurable 3D FPS-game-like environments for reinforcement learning
brain-agent - Brain Agent for Large-Scale and Multi-Task Agent Learning
episodic-transformer-memory-ppo - Clean baseline implementation of PPO using an episodic TransformerXL memory
DI-engine - OpenDILab Decision AI Engine
ppo-implementation-details - The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization
ml-agents - The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
adaptive-transformers-in-rl - Adaptive Attention Span for Reinforcement Learning
Gymnasium - An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)