Update README.md

zzmtsvv · Sep 14, 2023 · ab70e21 · ab70e21
1 parent 5eebcc6
commit ab70e21
Showing 1 changed file with 10 additions and 10 deletions.
diff --git a/README.md b/README.md
@@ -2,16 +2,16 @@
 `April 2023`: This repository contains experiments of different reinforcement learning algorithms applied to 3 MuJoCo environments - `Walker2d, Hopper and Halfcheetah`. Essentially, there are 2 models in comparison: Adaptive Behavior Cloning Regularization [1] (in short, `redq_bc`) and Supported Policy Optimization for Offline Reinforcement Learning [2] (in short, `spot`).<br /><br />
 `July-September 2023 update`: There are also additional implementations of:
 
-- Cal-QL [9] in `cal_ql`: [Logs](https://wandb.ai/zzmtsvv/cal_ql?workspace=user-zzmtsvv)
-- ReBRAC[11] in `rebrac`: [Logs](https://wandb.ai/zzmtsvv/ReBRAC?workspace=user-zzmtsvv)
-- EDAC[12] in `edac`: Logs: [EDAC itself](https://wandb.ai/zzmtsvv/EDAC?workspace=user-zzmtsvv), [SAC-N[12]](https://wandb.ai/zzmtsvv/SAC-N?workspace=user-zzmtsvv) (with `eta = 0`), [LB-SAC[16]](https://wandb.ai/zzmtsvv/LB-SAC?workspace=user-zzmtsvv) (with `eta = 0` and `batch_size = 10_000`)
-- AWAC[13] in `awac`: [Logs](https://wandb.ai/zzmtsvv/AWAC?workspace=user-zzmtsvv)
-- Decision Transformer[14] in `decision_transformer`: [Logs](https://wandb.ai/zzmtsvv/DecisionTransformer?workspace=user-zzmtsvv)
-- IQL[15] in `iql`: [Logs](https://wandb.ai/zzmtsvv/IQL?workspace=user-zzmtsvv)
-- MSG[17] in `msg`: [Logs](https://wandb.ai/zzmtsvv/MSG?workspace=user-zzmtsvv) (This method is realised upon offline SAC-N algorithm. However, my realization lacks appropriate hyperparameters for best results.)
-- PRDC[19] in `prdc`: [Logs](https://wandb.ai/zzmtsvv/PRDC?workspace=user-zzmtsvv)
-- DOGE[20] in `doge`: [Logs](https://wandb.ai/zzmtsvv/DOGE?workspace=user-zzmtsvv)
-- BEAR[21] in `bear`: [Logs](https://wandb.ai/zzmtsvv/BEAR?workspace=user-zzmtsvv)
+- Cal-QL [9]: [Logs](https://wandb.ai/zzmtsvv/cal_ql?workspace=user-zzmtsvv)
+- ReBRAC[11]: [Logs](https://wandb.ai/zzmtsvv/ReBRAC?workspace=user-zzmtsvv)
+- EDAC[12]: Logs: [EDAC itself](https://wandb.ai/zzmtsvv/EDAC?workspace=user-zzmtsvv), [SAC-N[12]](https://wandb.ai/zzmtsvv/SAC-N?workspace=user-zzmtsvv) (with `eta = 0`), [LB-SAC[16]](https://wandb.ai/zzmtsvv/LB-SAC?workspace=user-zzmtsvv) (with `eta = 0` and `batch_size = 10_000`)
+- AWAC[13]: [Logs](https://wandb.ai/zzmtsvv/AWAC?workspace=user-zzmtsvv)
+- Decision Transformer[14]: [Logs](https://wandb.ai/zzmtsvv/DecisionTransformer?workspace=user-zzmtsvv)
+- IQL[15]: [Logs](https://wandb.ai/zzmtsvv/IQL?workspace=user-zzmtsvv)
+- MSG[17]: [Logs](https://wandb.ai/zzmtsvv/MSG?workspace=user-zzmtsvv) (This method is realised upon offline SAC-N algorithm. However, my realization lacks appropriate hyperparameters for best results.)
+- PRDC[19]: [Logs](https://wandb.ai/zzmtsvv/PRDC?workspace=user-zzmtsvv)
+- DOGE[20]: [Logs](https://wandb.ai/zzmtsvv/DOGE?workspace=user-zzmtsvv)
+- BEAR[21]: [Logs](https://wandb.ai/zzmtsvv/BEAR?workspace=user-zzmtsvv)
 - SAC-RND[10]: [Logs](https://wandb.ai/zzmtsvv/sac_rnd?workspace=user-zzmtsvv) & [Implementation](https://github.com/zzmtsvv/sac_rnd)
 - RORL: [Logs](https://wandb.ai/zzmtsvv/RORL?workspace=user-zzmtsvv) & [Implementation](https://github.com/zzmtsvv/rorl) (lacks appropriate hyperparameters)
 - CNF[18]: [Logs](https://wandb.ai/zzmtsvv/CNF/workspace?workspace=user-zzmtsvv) & [Implementation](https://github.com/zzmtsvv/cnf)