DI-engine
episodic-transformer-memory-ppo
DI-engine | episodic-transformer-memory-ppo | |
---|---|---|
3 | 5 | |
2,553 | 109 | |
5.7% | - | |
8.7 | 2.5 | |
10 days ago | about 1 month ago | |
Python | Python | |
Apache License 2.0 | 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.
DI-engine
-
Anyone have experience with DI-Engine?
I posted a while back asking people what frameworks they were using for RL research. Recently i stumbled upon DI-Engine which looks promising! Actively maintained, with a diverse set of algorithms already implemented.
-
TransformerXL + PPO Baseline + MemoryGym
DI Engine
- Struggling with algorithm generality? Try DI engine; here is the solution
episodic-transformer-memory-ppo
-
Question about Transformer model input in RL
Check out this implementation https://github.com/MarcoMeter/episodic-transformer-memory-ppo
-
Using transformers in RL?
Maybe this easy-to-follow baseline implementation of PPO + TransformerXL is an inspiration for you.
-
What RL library supports custom LSTM and Transformer neural networks to use with algorithms such as PPO?
I provide baseline implementations on TransformerXL + PPO and LSTM/GRU + PPO. These are designed to be slim and easy-to-follow so that you can advance those implementations to the features and toolset that you need.
-
Trained a Transformer Decoder architecture with PPO, best way to maximize the entropy?
You can also checkout my baseline implementation of PPO + TrXL.
-
TransformerXL + PPO Baseline + MemoryGym
We finally completed a lightweight implementation of a memory-based agent using PPO and TransformerXL (and Gated TransformerXL).
What are some alternatives?
stable-baselines - A fork of OpenAI Baselines, implementations of reinforcement learning algorithms
godot_rl_agents - An Open Source package that allows video game creators, AI researchers and hobbyists the opportunity to learn complex behaviors for their Non Player Characters or agents
pytorch-a2c-ppo-acktr-gail - PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
Gymnasium - An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
tianshou - An elegant PyTorch deep reinforcement learning library.
popgym - Partially Observable Process Gym
seed_rl - SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.
recurrent-ppo-truncated-bptt - Baseline implementation of recurrent PPO using truncated BPTT
stable-baselines3 - PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
brain-agent - Brain Agent for Large-Scale and Multi-Task Agent Learning
on-policy - This is the official implementation of Multi-Agent PPO (MAPPO).
rl8 - A high throughput, end-to-end RL library for infinite horizon tasks.