SuperSuit
open_spiel
SuperSuit | open_spiel | |
---|---|---|
4 | 44 | |
432 | 4,004 | |
0.7% | 0.9% | |
8.0 | 9.5 | |
about 2 months ago | 3 days ago | |
Python | C++ | |
GNU General Public License v3.0 or later | 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.
SuperSuit
-
What is a wrapper in RL?
"SuperSuit is a library that includes all commonly used wrappers in RL (frame stacking, observation, normalization, etc.) for PettingZoo and Gym environments with a nice API. We developed it in lieu of wrappers built into PettingZoo. https://github.com/Farama-Foundation/SuperSuit "
-
Simple (few states) two-agent environments?
+1 on PettingZoo, and the wrappers they provide as SuperSuit come in handy as well!. Also check out OpenSpiel
- Take a look at SuperSuit- It contains mature versions of all common preprocessing wrappers for gym environments, including ones that accept lambda functions for observations/actions/rewards
-
Understanding multi agent learning in OpenAI gym and stable-baselines
Multi-agent isn’t supported by default in stable baselines, but you can make it work with PettingZoo. This example trains a single policy to control every agent in an environment (Parameter sharing). You could use these SuperSuit wrappers to work with other methods (self-play, independent learning, etc) but you would probably need to write some custom training code. https://github.com/PettingZoo-Team/SuperSuit#parallel-environment-vectorization
open_spiel
-
What projects or open-source contributions can impress Jane Street recruiters for a Quant SWE role ?
Deep mind actually has a repository where they applied this algorithm for incomplete-knowledge games. You could use it for reference: https://github.com/deepmind/open_spiel/tree/master/open_spiel/python/algorithms
-
I want to build a learning agent for a combinatorial game
+1. You can also find an implementation of Clobber and AlphaZero (and many other basic RL algorithms) in OpenSpiel: https://github.com/deepmind/open_spiel
-
minimax for imperfect-information turn-games?
You can find a lot of code online if you look, and many of these applied to Poker. There's a general implementation of both in Python and C++ in OpenSpiel, with some examples applied to small poker games. It's nice code to learn from because the algorithms operate over generic game descriptions, so there aren't game-specific design choices mixed up with the implementation of the algorithms, and you can create your own poker game and just run them on it.
-
OpenSpiel 1.3 Released!
And many other additions and improvements. See all the details here: https://github.com/deepmind/open_spiel/releases/tag/v1.3
-
What's a good OpenAI Gym Environment for applying centralized multi-agent learning using expected SARSA with tile coding?
I would checkout the openspiel package. It's main focus is RL in games (multi-agent environments). You'll find RL examples there and games that are small enough to solve without deep RL. There's also a wide range of environments from fully cooperative to adversarial zero-sum.
-
Competitive reinforcement learning for turn-based games
Hi, you can check out OpenSpiel: https://github.com/deepmind/open_spiel/
-
Reinforcement learning and Game Theory a turn-based game
as for algorithms , openspiel repository has few implementations some of these are not related to imperfect information games , and others are not for multiagent environment and others are tabular algorithms .
-
Shimmy 1.0: Gymnasium & PettingZoo bindings for popular external RL environments
This includes single-agent Gymnasium wrappers for DM Control, DM Lab, Behavior Suite, Arcade Learning Environment, OpenAI Gym V21 & V26. Multi-agent PettingZoo wrappers support DM Control Soccer, OpenSpiel and Melting Pot. For more information, read the release notes here:
-
How to deal with situations where the RL agent cannot act at every time step?
I've had some success using Action Masking - you can refer to here https://github.com/deepmind/open_spiel/blob/120420a74a69354d64c10b51cd129d4587f9f325/open_spiel/python/algorithms/dqn.py but for DQN you need to mask out q values for invalid actions (as well as masking them during prediction). In my case I'm able to place my mask in the observation so can fetch it quite easily during prediction but if that's not possible you could query it from the environment and store it in the replay buffer (like they do in the link I shared)
-
How to search the game tree with depth-first search?
Take a look at this simple implementation: https://github.com/deepmind/open_spiel/blob/master/open_spiel/algorithms/minimax.cc
What are some alternatives?
stable-baselines3 - PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
muzero-general - MuZero
stable-baselines - Mirror of Stable-Baselines: a fork of OpenAI Baselines, implementations of reinforcement learning algorithms
PettingZoo - An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities
gym - A toolkit for developing and comparing reinforcement learning algorithms.
stable-baselines - A fork of OpenAI Baselines, implementations of reinforcement learning algorithms
rlcard - Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.
kaggle-environments
gym-battleship - Battleship environment for reinforcement learning tasks
TexasHoldemSolverJava - A Java implemented Texas holdem and short deck Solver
tensortrade - An open source reinforcement learning framework for training, evaluating, and deploying robust trading agents.