tianshou
rlpyt
tianshou | rlpyt | |
---|---|---|
8 | 4 | |
7,459 | 2,197 | |
2.0% | - | |
9.5 | 0.0 | |
4 days ago | over 3 years 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.
tianshou
-
Is it better to not use the Target Update Frequency in Double DQN or depends on the application?
The tianshou implementation I found at https://github.com/thu-ml/tianshou/blob/master/tianshou/policy/modelfree/dqn.py is DQN by default.
- 他們能回來嗎
-
Multi-Agent Stable Baselines
https://github.com/thu-ml/tianshou Imho there isn't a library that has it all, RLlib is quite good too, but I think that Tianshou is more similar to Pytorch and that helps to change the internals more intuitively and know what you are doing.
-
Question about the old policy and new policy in TRPO code
Good point...I'll check in more detail when I get a chance later today! I would suggest looking at a more recent implementation like https://github.com/DLR-RM/stable-baselines3 or https://github.com/thu-ml/tianshou if you're trying to build. https://spinningup.openai.com/en/latest/algorithms/trpo.html is particularly good for understanding
-
Tensorflow vs PyTorch for A3C
Do you absolutely need A3C? A2C has become more widely used (see, e.g., the comment in https://github.com/ikostrikov/pytorch-a3c, and the fact that both https://github.com/thu-ml/tianshou and https://github.com/facebookresearch/salina have A2C implementations, but no A3C at first glance).
-
"Tianshou: a Highly Modularized Deep Reinforcement Learning Library", Weng et al 2021 (Python PyTorch MuJuCo; PPO, DQN, A2C, DDPG, SAC, TD3, REINFORCE, NPG, TRPO, ACKTR)
Code for https://arxiv.org/abs/2107.14171 found: https://github.com/thu-ml/tianshou/
Get the code for Tianshou here (GitHub).
-
Best PyTorch RL library for doing research
I tried tianshou and thought it was well-designed for modularity, but it was early in development when I tried and missing some basic features
rlpyt
-
About Prior Action Distribution in Entropy Regularized Actor-Critic Methods
The above example is from rlpyt library's SAC algorithm.
-
Best PyTorch RL library for doing research
I borrow a lot of performance tricks from sample factory, which is awesome but hard to modify from its original APPO algorithm. rlpyt was more modular, and I borrowed more ideas from it (namedarraytuple), but still too limited.
-
Spec for RL agent implementation?
rlpyt also has abstractions for additional things besides environments: https://github.com/astooke/rlpyt
-
PPO+LSTM Implementation
rlpyt is a library I’m studying right now, could be worth a shot; the code base is somewhat complex but after some reading it’s not so bad :)
What are some alternatives?
stable-baselines3 - PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
cleanrl - High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
gym - A toolkit for developing and comparing reinforcement learning algorithms.
ElegantRL - Massively Parallel Deep Reinforcement Learning. 🔥
minimalRL - Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
pytorch-learn-reinforcement-learning - A collection of various RL algorithms like policy gradients, DQN and PPO. The goal of this repo will be to make it a go-to resource for learning about RL. How to visualize, debug and solve RL problems. I've additionally included playground.py for learning more about OpenAI gym, etc.
acme - A library of reinforcement learning components and agents
seed_rl - SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.
sample-factory - High throughput synchronous and asynchronous reinforcement learning
pytorch-a3c - PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".