gym-multigrid
gym-simplegrid
gym-multigrid | gym-simplegrid | |
---|---|---|
1 | 2 | |
181 | 33 | |
- | - | |
0.0 | 5.4 | |
8 months ago | 19 days ago | |
Python | Python | |
Apache License 2.0 | 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.
gym-multigrid
-
INVALID_ARGUMENT: Received a label value of 8 which is outside the valid range of [0, 8). Label values: 8
So i am training an IPPO (Independent Proximal Policy Optimization) on the environment gym-multigrid, on the collect game (https://github.com/ArnaudFickinger/gym-multigrid). Actually i have 3 agents, each of them has its own actor and critic, and the actor has the following structure:
gym-simplegrid
-
SimpleGrid env for OpenAI gym
Check it out at: https://github.com/damat-le/gym-simplegrid
-
Best GridWorld environment?
Thank you everyone! In the end, I created a new simple environment from scratch. If you’re interested you can check it out at https://github.com/damat-le/gym-simplegrid
What are some alternatives?
agents-aea - A framework for autonomous economic agent (AEA) development
minihack - MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research
PettingZoo - An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities
dmc2gymnasium - Gymnasium integration for the DeepMind Control (DMC) suite
Minigrid - Simple and easily configurable grid world environments for reinforcement learning
santorini-RL - Play the board game Santorini with this Reinforcement Learning agent and custom Gym environment
Gym-Trading-Env - A simple, easy, customizable Gymnasium environment for trading.
gymprecice - A framework to design and develop reinforcement learning environments for single- and multi-physics active flow control.
pyTORCS-docker - Docker-based, gym-like torcs environment with vision.
pyreason-gym - An OpenAI wrapper for PyReason to use in a Grid World reinforcement learning setting
gym-gridverse - Gridworld domains in the gym interface