wassname/pytorch-soft-actor-critic
1
0
Fork 0
mirror of https://github.com/wassname/pytorch-soft-actor-critic.git synced 2026-06-27 16:46:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

Edit README.md & main.py

Browse Source
This commit is contained in:
pranz24
2019-09-16 16:34:56 +05:30
parent 6e49320c8c
commit 92486c2498
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+3 -3
View File
@@ -58,7 +58,7 @@ optional arguments:
True)
--gamma G discount factor for reward (default: 0.99)
--tau G target smoothing coefficient(τ) (default: 0.005)
--lr G learning rate (default: 3x10<sup>-4</sup>)
--lr G learning rate (default: 3e-4)
--alpha G Temperature parameter α determines the relative
importance of the entropy term against the reward
(default: 0.2)
@@ -66,14 +66,14 @@ optional arguments:
Automaically adjust α (default: False)
--seed N random seed (default: 123456)
--batch_size N batch size (default: 256)
--num_steps N maximum number of steps (default: 10<sup>6</sup>)
--num_steps N maximum number of steps (default: 1e6)
--hidden_size N hidden size (default: 256)
--updates_per_step N model updates per simulator step (default: 1)
--start_steps N Steps sampling random actions (default: 10<sup>4</sup>)
--target_update_interval N
Value target update per no. of updates per step
(default: 1)
--replay_size N size of replay buffer (default: 10<sup>6</sup>)
--replay_size N size of replay buffer (default: 1e6)
--cuda run on CUDA (default: False)
```