popgym
Ray
popgym | Ray | |
---|---|---|
4 | 43 | |
147 | 31,414 | |
8.8% | 2.5% | |
6.1 | 10.0 | |
about 2 months ago | 4 days ago | |
Python | Python | |
MIT License | 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.
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.
Ray
- Ray: Unified framework for scaling AI and Python applications
-
Open Source Advent Fun Wraps Up!
22. Ray | Github | tutorial
-
Fine-Tuning Llama-2: A Comprehensive Case Study for Tailoring Custom Models
Training times for GSM8k are mentioned here: https://github.com/ray-project/ray/tree/master/doc/source/te...
- Ray – an open source project for scaling AI workloads
-
Methods to keep agents inside grid world.
Here's a reference from RLlib that points to docs and an example, and here's one from one of my projects that includes all my own implementations
-
TransformerXL + PPO Baseline + MemoryGym
RLlib
- Is dynamic action masking possible in Rllib?
-
AWS re:Invent 2022 Recap | Data & Analytics services
⦿ AWS Glue Data Quality - Automatic data quality rule recommendations based on your data AWS Glue for Ray - Data integration with Ray (ray.io), a popular new open-source compute framework that helps you scale Python workloads
-
Think about it for a second
https://ray.io (just dropping the link)
-
Elixir Livebook now as a desktop app
I've wondered whether it's easier to add data analyst stuff to Elixir that Python seems to have, or add features to Python that Erlang (and by extension Elixir) provides out of the box.
By what I can see, if you want multiprocessing on Python in an easier way (let's say running async), you have to use something like ray core[0], then if you want multiple machines you need redis(?). Elixir/Erlang supports this out of the box.
Explorer[1] is an interesting approach, where it uses Rust via Rustler (Elixir library to call Rust code) and uses Polars as its dataframe library. I think Rustler needs to be reworked for this usecase, as it can be slow to return data. I made initial improvements which drastically improves encoding (https://github.com/elixir-nx/explorer/pull/282 and https://github.com/elixir-nx/explorer/pull/286, tldr 20+ seconds down to 3).
[0] https://github.com/ray-project/ray
What are some alternatives?
recurrent-ppo-truncated-bptt - Baseline implementation of recurrent PPO using truncated BPTT
optuna - A hyperparameter optimization framework
brain-agent - Brain Agent for Large-Scale and Multi-Task Agent Learning
stable-baselines3 - PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
episodic-transformer-memory-ppo - Clean baseline implementation of PPO using an episodic TransformerXL memory
Faust - Python Stream Processing
ppo-implementation-details - The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization
gevent - Coroutine-based concurrency library for Python
adaptive-transformers-in-rl - Adaptive Attention Span for Reinforcement Learning
stable-baselines - A fork of OpenAI Baselines, implementations of reinforcement learning algorithms
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.
SCOOP (Scalable COncurrent Operations in Python) - SCOOP (Scalable COncurrent Operations in Python)