pytorch-a2c-ppo-acktr-gail
f-IRL
| pytorch-a2c-ppo-acktr-gail | f-IRL | |
|---|---|---|
| 3 | 2 | |
| 3,423 | 35 | |
| - | - | |
| 0.0 | 1.8 | |
| almost 2 years ago | 10 months 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.
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).
f-IRL
-
Can you use the reward learned in generative adversarial imitation learning in order to train from scratch?
Code for https://arxiv.org/abs/2011.04709 found: https://github.com/twni2016/f-IRL
-
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.
What are some alternatives?
Super-mario-bros-PPO-pytorch - Proximal Policy Optimization (PPO) algorithm for Super Mario Bros
Meta-SAC - Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient - 7th ICML AutoML workshop 2020
soft-actor-critic - Implementation of the Soft Actor Critic algorithm using Pytorch.
falken - Falken provides developers with a service that allows them to train AI that can play their games
dm_control - Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
ElegantRL - Massively Parallel Deep Reinforcement Learning. 🔥
tensorforce - Tensorforce: a TensorFlow library for applied reinforcement learning
eirli - An Empirical Investigation of Representation Learning for Imitation (EIRLI), NeurIPS'21
TensorFlow2.0-for-Deep-Reinforcement-Learning - TensorFlow 2.0 for Deep Reinforcement Learning. :octopus:
imitation - Clean PyTorch implementations of imitation and reward learning algorithms
PCGrad - Code for "Gradient Surgery for Multi-Task Learning"
tianshou - An elegant PyTorch deep reinforcement learning library.