ShangtongZhang DeepRL issues

ShangtongZhang / DeepRL

Modularized Implementation of Deep RL Algorithms in PyTorch

MIT License

3.21k stars 684 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

SAC example?

#111 fansstan opened 6 months ago
0
replay buffer: why next state start index is n_steps after state start index?

#110 TaciturnMute closed 1 year ago
0
Double constraints for updating actor?

#109 KhoiDOO opened 1 year ago
0
Does the DAC code apply to robotics environment?

#108 data-null123 opened 3 years ago
1
config parameters

#107 JordanAsh opened 3 years ago
0
Continuous Control Reward and State Normalization

#106 xkianteb closed 3 years ago
0
Passing info from Actor to Agent in Async implementation?

#105 Louis-Bagot opened 3 years ago
0
How to obtain the policy(logits) rather than only the actions from self.actor.step()

#104 fuxianh closed 3 years ago
2
fix a minor issue replay.py

#103 ainilaha opened 4 years ago
0
Question about QUOTA-discrete

#102 yingnan-rl closed 4 years ago
4
Question about DeepRL-QUOTA-discrete

#101 yingnan-rl closed 4 years ago
0
Reference for the network design

#100 tilmto closed 4 years ago
2
Adding elements to the Transition namedtuple

#99 Louis-Bagot closed 4 years ago
3
Asynchronous DQN

#98 Louis-Bagot closed 4 years ago
4
dqn_pixel doesn't work under the multiprocess setting of "config.num_workers = 5"

#97 momofive closed 4 years ago
1
Bump tensorflow from 1.15.0 to 1.15.4

#96 dependabot[bot] closed 4 years ago
1
How much rewards can we get using DQN to play atari games usually?

#95 DeepDuke closed 4 years ago
0
Add baselines to requirements.txt

#94 psurya1994 closed 4 years ago
1
using target network to calculate last state value

#93 backpropper closed 4 years ago
4
I want to get the experimental data used to plot, if you are willing to

#92 THSWind closed 4 years ago
2
How to get averaged curve of PPO online performance on Mujoco?

#91 KarlXing closed 4 years ago
2
no module named baselines

#90 AprilXiaoyanLiu closed 4 years ago
2
How can I use this package in python 3.7?

#89 jiang-yuan closed 4 years ago
1
N-step target not working

#88 ShangtongZhang opened 4 years ago
3
Option Critic e-greedy option update question

#87 spacegoing closed 4 years ago
2
Option Critic Q value update question

#86 spacegoing closed 4 years ago
6
Prioritized experience replay issue

#85 Rajawat23 closed 4 years ago
1
N-step target in the rainbow implementation

#84 ShangtongZhang closed 4 years ago
1
fix a bug in replay

#83 mingfeisun closed 4 years ago
1
CUDA multiprocessing error

#82 spacegoing closed 4 years ago
7
How to plot the result of OC?

#81 RushToNeverLand closed 4 years ago
1
[Question] VecEnv implementation

#80 bycn closed 4 years ago
1
Is there any method to install baselines:8e56dd?

#79 RushToNeverLand closed 4 years ago
1
Training using AsyncReplay gets stuck after arounf 50k steps.

#78 ayooshkathuria closed 4 years ago
1
LSTM for PPOC

#77 spacegoing closed 4 years ago
4
Bump tensorflow from 1.12.0 to 1.15.2

#76 dependabot[bot] closed 4 years ago
1
Environments usage permission

#75 lich14 closed 4 years ago
2
Can not find cheetah backward

#74 lich14 closed 4 years ago
1
Option-Critic Beta Advantage Question

#73 spacegoing closed 4 years ago
6
Bump tensorflow from 1.12.0 to 1.15.0

#72 dependabot[bot] closed 4 years ago
1
Why use policy over option's q value (Q_Omega) for intra-option policy updates?

#71 spacegoing closed 4 years ago
1
Is there any docker container on docker hub

#70 spacegoing closed 4 years ago
1
Some questions about DAC

#69 Sunkworld closed 4 years ago
2
test code running give unexpected results

#68 fuxianh closed 4 years ago
2
Random seed is fixed across runs

#67 rpinsler closed 5 years ago
2
Running multiple environments

#66 neale closed 5 years ago
4
size mismatch error for Gym Toy text environments

#65 RaviTej310 closed 4 years ago
1
How to implement eval_step() in BaseAgent()

#64 forhonourlx closed 4 years ago
1
set_one_thread() in example.py

#63 jyf588 closed 5 years ago
6
name 'random_seed(seed)' is not defined

#62 yongqianxiao closed 5 years ago
1