Skip to content

Commit 610914f

Browse files
authoredMar 17, 2021
Stable-Baselines3 v1.0 (#72)
1 parent 14a5a6a commit 610914f

File tree

3 files changed

+23
-4
lines changed

3 files changed

+23
-4
lines changed
 

‎README.md

+20-1
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,12 @@
66

77
<!-- <img src="images/BipedalWalkerHardcorePPO.gif" align="right" width="35%"/> -->
88

9-
A Training Framework for Reinforcement Learning (RL), together with a collection of trained agents, with tuned hyperparameters, using [Stable Baselines3](https://github.com/DLR-RM/stable-baselines3).
9+
RL Baselines3 Zoo is a training framework for Reinforcement Learning (RL), using [Stable Baselines3](https://github.com/DLR-RM/stable-baselines3).
10+
11+
It provides scripts for training, evaluating agents, tuning hyperparameters, plotting results and recording videos.
12+
13+
In addition, it includes a collection of tuned hyperparameters for common environments and RL algorithms, and agents trained with those settings.
14+
1015

1116
We are **looking for contributors** to complete the collection!
1217

@@ -60,6 +65,20 @@ Plot scripts (to be documented, see "Results" sections in SB3 documentation):
6065
- `scripts/all_plots.py`/`scripts/plot_from_file.py` for plotting evaluations
6166
- `scripts/plot_train.py` for plotting training reward/success
6267

68+
*Examples (on the current collection)*
69+
70+
Plot training success (y-axis) w.r.t. timesteps (x-axis) with a moving window of 500 episodes for all the `Fetch` environment with `HER` algorithm:
71+
72+
```
73+
python scripts/plot_train.py -a her -e Fetch -y success -f rl-trained-agents/ -w 500 -x steps
74+
```
75+
76+
Plot evaluation reward curve for TQC, SAC and TD3 on the HalfCheetah and Ant PyBullet environments:
77+
78+
```
79+
python scripts/all_plots.py -a sac td3 tqc --env HalfCheetah Ant -f rl-trained-agents/
80+
```
81+
6382
## Custom Environment
6483

6584
The easiest way to add support for a custom environment is to edit `utils/import_envs.py` and register your environment here. Then, you need to add a section for it in the hyperparameters file (`hyperparams/algo.yml`).

‎requirements.txt

+2-2
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
stable-baselines3[extra,tests,docs]>=1.0rc2
1+
stable-baselines3[extra,tests,docs]>=1.0
22
box2d-py==2.3.8
33
pybullet
44
gym-minigrid
@@ -7,4 +7,4 @@ optuna
77
pytablewriter
88
seaborn
99
pyyaml>=5.1
10-
sb3-contrib>=1.0rc1
10+
sb3-contrib>=1.0

‎version.txt

+1-1
Original file line numberDiff line numberDiff line change
@@ -1 +1 @@
1-
1.0rc2
1+
1.0

0 commit comments

Comments
 (0)
Please sign in to comment.