|
|
c8fdd11d8c
|
Outputting only 3 channels from the decoder
|
2023-04-12 17:30:20 +02:00 |
|
|
|
a83149f61e
|
Keeping channels as 3
|
2023-04-12 17:29:50 +02:00 |
|
|
|
1f4667a08d
|
Adding preprocessing function
|
2023-04-12 17:16:47 +02:00 |
|
|
|
7d7387bd5d
|
Adding target value function updates and momentum updates
|
2023-04-12 17:15:17 +02:00 |
|
|
|
9085abe684
|
Correcting UB loss
|
2023-04-12 09:34:11 +02:00 |
|
|
|
5ded7bc8f1
|
Adding actor and value learners
|
2023-04-12 09:33:42 +02:00 |
|
|
|
cc48b0b0f8
|
Adding Rewards
|
2023-04-12 09:33:19 +02:00 |
|
|
|
ac714e3495
|
Correct history with detach
|
2023-04-10 20:18:39 +02:00 |
|
|
|
de17cab9f5
|
Add MOCO to introduce lower bound loss
|
2023-04-10 20:18:17 +02:00 |
|
|
|
05dd20cdfa
|
Add a class to freeze parameters
|
2023-04-10 20:17:44 +02:00 |
|
|
|
8fd56ba94d
|
Adding model architecture for Reward, Value and Target Value
|
2023-04-10 13:18:41 +02:00 |
|
|
|
47090449d1
|
Adding Reward, Value and Target Value models
|
2023-04-10 13:18:08 +02:00 |
|
|
|
c4283ced6f
|
Changing CLUB loss and Tensor stacking
|
2023-04-09 18:23:16 +02:00 |
|
|
|
6b4762d5fc
|
Changing Upper Bound loss
|
2023-04-09 18:22:41 +02:00 |
|
|
|
5caea7695a
|
Changing variable reshaping strategy
|
2023-04-09 18:22:12 +02:00 |
|
|
|
ada3cadf0c
|
Adding momentum encoder
|
2023-04-02 18:52:46 +02:00 |
|
|
|
d9d350e191
|
Adding Contrastive learning models
|
2023-04-02 18:52:26 +02:00 |
|
|
|
7c9e75030b
|
Updating value model to be stochastic
|
2023-03-31 19:12:46 +02:00 |
|
|
|
e6e11f90b7
|
Adding value model
|
2023-03-31 18:38:51 +02:00 |
|
|
|
4e1ef89924
|
Adding action network
|
2023-03-31 18:00:07 +02:00 |
|
|
|
13765c2f9e
|
Adding action decoder
|
2023-03-31 17:59:42 +02:00 |
|
|
|
47a0772c9d
|
Replacing seed with version name variable in environment id naming
|
2023-03-28 20:22:27 +02:00 |
|
|
|
d558b9f558
|
Changing names for clean and noisy environments via version
|
2023-03-28 20:21:58 +02:00 |
|
|
|
41dcf22262
|
Collecting dataset from noiseless environment
|
2023-03-28 20:21:26 +02:00 |
|
|
|
11f00ad695
|
Add encoder loss and include tqdm for visualization
|
2023-03-27 19:23:42 +02:00 |
|
|
|
a1fe81f018
|
Grouping for actions too
|
2023-03-27 19:22:47 +02:00 |
|
|
|
38cc645253
|
Update models to give distribution as well in the output
|
2023-03-27 19:22:17 +02:00 |
|
|
|
a351134f08
|
Deleting unnecessary files
|
2023-03-25 17:53:04 +01:00 |
|
|
|
ab2b6599c1
|
File formatting
|
2023-03-25 17:51:34 +01:00 |
|
|
|
4515c6a6b7
|
Detecting and removing corrupt video files from the dataset
|
2023-03-25 17:36:58 +01:00 |
|
|
|
25c2853ba6
|
Adding high noise by randomising the frames
|
2023-03-25 17:07:07 +01:00 |
|
|
|
f2aa9baebb
|
Removing ground plane from observations
|
2023-03-25 14:19:56 +01:00 |
|
|
|
8464503dd8
|
Adding new background videos for each episode
|
2023-03-25 14:18:07 +01:00 |
|
|
|
43f862ee6d
|
Minor editing changes in comments
|
2023-03-24 20:41:28 +01:00 |
|
|
|
641c9bd57c
|
Implementing ICLUB
|
2023-03-24 20:39:14 +01:00 |
|
|
|
abaca2bea9
|
Adding Denoised Predictive Imagination
|
2023-03-23 15:05:28 +01:00 |
|
ved1
|
69d1528077
|
Adding Empowerment functions
|
2023-02-23 16:49:55 +01:00 |
|
ved1
|
961e46c347
|
Adding Klyubin Mazeworld
|
2023-02-23 12:39:03 +01:00 |
|
ved1
|
80760bb686
|
Adding PPO
|
2023-02-01 19:36:09 +01:00 |
|
ved1
|
000b970a12
|
A3C+ICM
|
2023-01-31 15:58:50 +01:00 |
|
ved1
|
c3f6e9f281
|
Cartpole Example
|
2023-01-30 17:59:26 +01:00 |
|
ved1
|
18dd8cc8cf
|
Neural Network Models
|
2023-01-30 17:59:11 +01:00 |
|
ved1
|
bc1b46247d
|
Mario Environment
|
2023-01-30 17:58:53 +01:00 |
|
ved1
|
0781d4fd05
|
Changing main file
|
2023-01-30 17:57:49 +01:00 |
|
ved1
|
6441759199
|
Adding ICM file
|
2023-01-27 19:32:44 +01:00 |
|
|
|
6f8dfca105
|
Initial commit
|
2023-01-27 14:42:55 +00:00 |
|
