uidilr / Gail_ppo_tf
Licence: mit
Tensorflow implementation of Generative Adversarial Imitation Learning(GAIL) with discrete action
Stars: ✭ 99
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Gail ppo tf
Easy Rl
强化学习中文教程，在线阅读地址：https://datawhalechina.github.io/easy-rl/
Stars: ✭ 3,004 (+2934.34%)
Mutual labels: ppo, imitation-learning
Tianshou
An elegant PyTorch deep reinforcement learning library.
Stars: ✭ 4,109 (+4050.51%)
Mutual labels: ppo, imitation-learning
imitation learning
PyTorch implementation of some reinforcement learning algorithms: A2C, PPO, Behavioral Cloning from Observation (BCO), GAIL.
Stars: ✭ 93 (-6.06%)
Mutual labels: imitation-learning, ppo
Gym Continuousdoubleauction
A custom MARL (multi-agent reinforcement learning) environment where multiple agents trade against one another (self-play) in a zero-sum continuous double auction. Ray [RLlib] is used for training.
Stars: ✭ 50 (-49.49%)
Mutual labels: ppo
Pgdrive
PGDrive: an open-ended driving simulator with infinite scenes from procedural generation
Stars: ✭ 60 (-39.39%)
Mutual labels: imitation-learning
Run Skeleton Run
Reason8.ai PyTorch solution for NIPS RL 2017 challenge
Stars: ✭ 83 (-16.16%)
Mutual labels: ppo
Deeprl algorithms
DeepRL algorithms implementation easy for understanding and reading with Pytorch and Tensorflow 2(DQN, REINFORCE, VPG, A2C, TRPO, PPO, DDPG, TD3, SAC)
Stars: ✭ 97 (-2.02%)
Mutual labels: ppo
Slm Lab
Modular Deep Reinforcement Learning framework in PyTorch. Companion library of the book "Foundations of Deep Reinforcement Learning".
Stars: ✭ 904 (+813.13%)
Mutual labels: ppo
Hand dapg
Repository to accompany RSS 2018 paper on dexterous hand manipulation
Stars: ✭ 88 (-11.11%)
Mutual labels: imitation-learning
Torch Ac
Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms A2C and PPO
Stars: ✭ 70 (-29.29%)
Mutual labels: ppo
Dogtorch
Who Let The Dogs Out? Modeling Dog Behavior From Visual Data https://arxiv.org/pdf/1803.10827.pdf
Stars: ✭ 66 (-33.33%)
Mutual labels: imitation-learning
Sc2aibot
Implementing reinforcement-learning algorithms for pysc2 -environment
Stars: ✭ 83 (-16.16%)
Mutual labels: ppo
Torchrl
Pytorch Implementation of Reinforcement Learning Algorithms ( Soft Actor Critic(SAC)/ DDPG / TD3 /DQN / A2C/ PPO / TRPO)
Stars: ✭ 90 (-9.09%)
Mutual labels: ppo
Deterministic Gail Pytorch
PyTorch implementation of Deterministic Generative Adversarial Imitation Learning (GAIL) for Off Policy learning
Stars: ✭ 44 (-55.56%)
Mutual labels: imitation-learning
Imitation Learning
Imitation learning algorithms
Stars: ✭ 85 (-14.14%)
Mutual labels: imitation-learning
On Policy
This is the official implementation of Multi-Agent PPO.
Stars: ✭ 63 (-36.36%)
Mutual labels: ppo
Imitation Learning
Autonomous driving: Tensorflow implementation of the paper "End-to-end Driving via Conditional Imitation Learning"
Stars: ✭ 60 (-39.39%)
Mutual labels: imitation-learning
Inverse rl
Adversarial Imitation Via Variational Inverse Reinforcement Learning
Stars: ✭ 79 (-20.2%)
Mutual labels: imitation-learning
Generative Adversarial Imitation Learning
Implementation of Generative Adversarial Imitation Learning(GAIL) using tensorflow
Dependencies
python>=3.5
tensorflow>=1.4
gym>=0.9.3
Gym environment
Env==CartPole-v0
State==Continuous
Action==Discrete
Usage
Train experts
python3 run_ppo.py
Sample trajectory using expert
python3 sample_trajectory.py
Run GAIL
python3 run_gail.py
Run supervised learning
python3 run_behavior_clone.py
Test trained policy
python3 test_policy.py
Default policy is trained with gail
--alg=bc or ppo allows you to change test policy
If you want to test bc policy, specify the number of model.ckpt-number in the directory trained_models/bc
Example
python3 test_policy.py --alg=bc --model=1000
Tensorboard
tensorboard --logdir=log
Results
 |
 |
|---|---|
| Fig.1 Training results | legend |
LICENSE
MIT LICENSE
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].