DeepCubeA
pytorch-a2c-ppo-acktr-gail
| DeepCubeA | pytorch-a2c-ppo-acktr-gail | |
|---|---|---|
| 1 | 3 | |
| 141 | 3,423 | |
| - | - | |
| 5.2 | 0.0 | |
| 9 months ago | almost 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.
DeepCubeA
-
DeepRL and Rubik’s Cube
We are looking at Rubik’s Cube as target problem, and kicking off a project which will start from https://github.com/forestagostinelli/DeepCubeA and go from there.
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?
Muzero - Pytorch Implementation of MuZero for gym environment. It support any Discrete , Box and Box2D configuration for the action space and observation space.
Super-mario-bros-PPO-pytorch - Proximal Policy Optimization (PPO) algorithm for Super Mario Bros
PPO-PyTorch - Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch
soft-actor-critic - Implementation of the Soft Actor Critic algorithm using Pytorch.
min2phase - Rubik's Cube Solver. An optimized implementation of Kociemba's two-phase algorithm.
dm_control - Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
Muzero-unplugged - Pytorch Implementation of MuZero Unplugged for gym environment. This algorithm is capable of supporting a wide range of action and observation spaces, including both discrete and continuous variations.
tensorforce - Tensorforce: a TensorFlow library for applied reinforcement learning
minimalRL - Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
TensorFlow2.0-for-Deep-Reinforcement-Learning - TensorFlow 2.0 for Deep Reinforcement Learning. :octopus:
muzero-general - MuZero
PCGrad - Code for "Gradient Surgery for Multi-Task Learning"