DeepX-inc machina issues

DeepX-inc / machina

Control section: Deep Reinforcement Learning framework

MIT License

279 stars 43 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Remove pds (probabilistic distributions) class and incorporating to pol (policy) class.

#166 rarilurelo opened 5 years ago
0
Add version information

#165 iory closed 5 years ago
0
rew_func is defined in the test_learning

#164 rarilurelo closed 5 years ago
0
Add action info of argmax qf pol

#163 takerfume closed 5 years ago
1
fix log_std in gaussian with rnn

#162 rarilurelo closed 5 years ago
0
log_std referenced before assignment

#161 jtoyama4 closed 5 years ago
2
fix pytorch version

#160 rarilurelo closed 5 years ago
0
Check package verision in travis

#159 takerfume closed 5 years ago
0
fix dependency of gym 0.10.5

#158 rarilurelo closed 5 years ago
0
Remove lambda from prioritized ddpg

#157 takerfume closed 5 years ago
1
Change imiation doc a little

#156 takerfume closed 5 years ago
0
Testing policy distillation

#155 pwuethri closed 5 years ago
2
Create IMITATION.md

#154 takerfume closed 5 years ago
1
Create IMITATION.md

#153 takerfume closed 5 years ago
0
Add names of implemented algorithms to readme

#152 rarilurelo closed 5 years ago
0
Add taking movie retry

#151 takerfume closed 5 years ago
0
Add option of off traj size

#150 takerfume closed 5 years ago
4
Fix bug of run_ddpg

#149 takerfume closed 5 years ago
0
[WIP] add test

#148 takerfume closed 5 years ago
25
Fix bug of imitation

#147 takerfume closed 5 years ago
1
Add taking movie retry

#146 takerfume closed 5 years ago
0
Add taking movie

#145 takerfume closed 5 years ago
0
add cpu_mode in sampling

#144 rarilurelo closed 5 years ago
0
Use cpu_mode in sampling phase

#143 rarilurelo closed 5 years ago
1
Add Explanation about Imitation Learning

#142 takerfume closed 5 years ago
0
Fix bug of check acs obs

#141 takerfume closed 5 years ago
1
DIAYN implementation

#140 ven-kyoshiro closed 5 years ago
1
Test for new algorithm

#139 rarilurelo closed 5 years ago
2
Teacher and On-Policy distillation

#138 pwuethri closed 5 years ago
13
Add qt opt

#137 takerfume closed 5 years ago
10
add rule for variable

#136 rarilurelo closed 5 years ago
1
[wip]

#135 rarilurelo closed 5 years ago
3
wrap map object with list

#134 rarilurelo closed 5 years ago
0
Write meanings of args

#133 takerfume closed 5 years ago
1
Script for taking movies of learned policy

#132 takerfume closed 5 years ago
0
Airl gail ddpg fix

#131 takerfume closed 5 years ago
1
QT-Opt

#130 takerfume closed 5 years ago
1
Variational Discriminator Bottleneck

#129 takerfume opened 5 years ago
0
Implement Recurrent Model Predictive Control

#128 jinbeizame007 closed 5 years ago
1
remove

#127 rarilurelo closed 5 years ago
0
Improving sac from https://arxiv.org/pdf/1812.05905.pdf

#126 rarilurelo closed 5 years ago
0
Learning Self-Imitating Diverse Policies

#125 takerfume opened 5 years ago
0
Implement AIRL

#124 takerfume closed 5 years ago
1
Fix typo traj.step to traj.iterate_step

#123 takerfume closed 5 years ago
0
Adversarial Inverse Reinforcement Learning

#122 takerfume closed 5 years ago
1
Allocate Traj's tensor to cpu

#121 rarilurelo closed 5 years ago
1
Implement Model Predictive Control

#120 jinbeizame007 closed 5 years ago
3
Managing number of steps in a batch

#119 rarilurelo opened 5 years ago
1
Inappropriate mean in loss_functional with rnn

#118 rarilurelo closed 5 years ago
1
Normalize pgweight sac

#117 rarilurelo closed 5 years ago
0

Previous Next