pyagents
pytorch-a2c-ppo-acktr-gail
| pyagents | pytorch-a2c-ppo-acktr-gail | |
|---|---|---|
| 1 | 3 | |
| 3 | 3,491 | |
| - | - | |
| 4.8 | 0.0 | |
| 11 months ago | about 2 years ago | |
| Python | Python | |
| - | 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.
pyagents
-
Understanding RL – repo sharing
One improvement (especially from an OOP perspective) could be to have two abstract classes for on-policy and off-policy algorithms, as in general they behave differently (at training time). That's an abstraction I implemented in my own RL playground, feel free to take a look if you're interested: https://github.com/diegochine/pyagents
pytorch-a2c-ppo-acktr-gail
-
How does advantage estimation is done when episodes are of variable length in PPO?
As an example look at "compute_returns" function here (and pay attention to how self.masks is used): https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail/blob/master/a2c_ppo_acktr/storage.py
-
How to pretrain a model on expert data?
Try using an imitation learning algorithm. Two popular options are MaxEnt IRL and GAIL. This repository has GAIL implementation and this repository has MaxEnt IRL and GAIL implementation. There are other implementations too that you can check out.
-
Trying to Train PPO Agent for Pendulum-v0 from Pixel Inputs
For the PPO, I used this repo, which includes most tricks including GAE, normalized rewards, etc. I have verified this repo works for the traditional Pendulum-v0 task and Atari games (Pong and Breakout).
What are some alternatives?
ppo-implementation-details - The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization
Super-mario-bros-PPO-pytorch - Proximal Policy Optimization (PPO) algorithm for Super Mario Bros
trax - Trax — Deep Learning with Clear Code and Speed
soft-actor-critic - Implementation of the Soft Actor Critic algorithm using Pytorch.
minimalRL - Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
dm_control - Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
tensorforce - Tensorforce: a TensorFlow library for applied reinforcement learning
TensorFlow2.0-for-Deep-Reinforcement-Learning - TensorFlow 2.0 for Deep Reinforcement Learning. :octopus:
PCGrad - Code for "Gradient Surgery for Multi-Task Learning"
DI-engine - OpenDILab Decision AI Engine
Reinforcement-Learning - Learn Deep Reinforcement Learning in 60 days! Lectures & Code in Python. Reinforcement Learning + Deep Learning
pomdp-baselines - Simple (but often Strong) Baselines for POMDPs in PyTorch, ICML 2022