-
Notifications
You must be signed in to change notification settings - Fork 4.1k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Add Soft Actor-Critic as trainer option (#2341)
* Add Soft Actor-Critic model, trainer, and policy and sac_trainer_config.yaml * Add documentation for SAC and tweak PPO documentation to reference the new pages. * Add tests for SAC, change simple_rl test to run both PPO and SAC.
- Loading branch information
Ervin T
committed
Sep 6, 2019
1 parent
d150c51
commit 5cd2118
Showing
17 changed files
with
3,064 additions
and
133 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,276 @@ | ||
default: | ||
trainer: sac | ||
batch_size: 128 | ||
buffer_size: 50000 | ||
buffer_init_steps: 0 | ||
hidden_units: 128 | ||
init_entcoef: 1.0 | ||
learning_rate: 3.0e-4 | ||
max_steps: 5.0e4 | ||
memory_size: 256 | ||
normalize: false | ||
num_update: 1 | ||
train_interval: 1 | ||
num_layers: 2 | ||
time_horizon: 64 | ||
sequence_length: 64 | ||
summary_freq: 1000 | ||
tau: 0.005 | ||
use_recurrent: false | ||
vis_encode_type: default | ||
reward_signals: | ||
extrinsic: | ||
strength: 1.0 | ||
gamma: 0.99 | ||
|
||
BananaLearning: | ||
normalize: false | ||
batch_size: 256 | ||
buffer_size: 500000 | ||
max_steps: 1.0e5 | ||
init_entcoef: 0.05 | ||
train_interval: 1 | ||
|
||
VisualBananaLearning: | ||
beta: 1.0e-2 | ||
gamma: 0.99 | ||
num_epoch: 1 | ||
max_steps: 5.0e5 | ||
summary_freq: 1000 | ||
|
||
BouncerLearning: | ||
normalize: true | ||
beta: 0.0 | ||
max_steps: 5.0e5 | ||
num_layers: 2 | ||
hidden_units: 64 | ||
summary_freq: 1000 | ||
|
||
PushBlockLearning: | ||
max_steps: 5.0e4 | ||
init_entcoef: 0.05 | ||
beta: 1.0e-2 | ||
hidden_units: 256 | ||
summary_freq: 2000 | ||
time_horizon: 64 | ||
num_layers: 2 | ||
|
||
SmallWallJumpLearning: | ||
max_steps: 1.0e6 | ||
hidden_units: 256 | ||
summary_freq: 2000 | ||
time_horizon: 128 | ||
init_entcoef: 0.1 | ||
num_layers: 2 | ||
normalize: false | ||
|
||
BigWallJumpLearning: | ||
max_steps: 1.0e6 | ||
hidden_units: 256 | ||
summary_freq: 2000 | ||
time_horizon: 128 | ||
num_layers: 2 | ||
init_entcoef: 0.1 | ||
normalize: false | ||
|
||
StrikerLearning: | ||
max_steps: 5.0e5 | ||
learning_rate: 1e-3 | ||
beta: 1.0e-2 | ||
hidden_units: 256 | ||
summary_freq: 2000 | ||
time_horizon: 128 | ||
init_entcoef: 0.1 | ||
num_layers: 2 | ||
normalize: false | ||
|
||
GoalieLearning: | ||
max_steps: 5.0e5 | ||
learning_rate: 1e-3 | ||
beta: 1.0e-2 | ||
hidden_units: 256 | ||
summary_freq: 2000 | ||
time_horizon: 128 | ||
init_entcoef: 0.1 | ||
num_layers: 2 | ||
normalize: false | ||
|
||
PyramidsLearning: | ||
summary_freq: 2000 | ||
time_horizon: 128 | ||
batch_size: 128 | ||
buffer_init_steps: 10000 | ||
buffer_size: 500000 | ||
hidden_units: 256 | ||
num_layers: 2 | ||
init_entcoef: 0.01 | ||
max_steps: 5.0e5 | ||
sequence_length: 16 | ||
tau: 0.01 | ||
use_recurrent: false | ||
reward_signals: | ||
extrinsic: | ||
strength: 2.0 | ||
gamma: 0.99 | ||
gail: | ||
strength: 0.02 | ||
gamma: 0.99 | ||
encoding_size: 128 | ||
use_actions: true | ||
demo_path: demos/ExpertPyramid.demo | ||
|
||
VisualPyramidsLearning: | ||
time_horizon: 128 | ||
batch_size: 64 | ||
hidden_units: 256 | ||
buffer_init_steps: 1000 | ||
num_layers: 1 | ||
beta: 1.0e-2 | ||
max_steps: 5.0e5 | ||
buffer_size: 500000 | ||
init_entcoef: 0.01 | ||
tau: 0.01 | ||
reward_signals: | ||
extrinsic: | ||
strength: 2.0 | ||
gamma: 0.99 | ||
gail: | ||
strength: 0.02 | ||
gamma: 0.99 | ||
encoding_size: 128 | ||
use_actions: true | ||
demo_path: demos/ExpertPyramid.demo | ||
|
||
3DBallLearning: | ||
normalize: true | ||
batch_size: 64 | ||
buffer_size: 12000 | ||
summary_freq: 1000 | ||
time_horizon: 1000 | ||
hidden_units: 64 | ||
init_entcoef: 0.5 | ||
max_steps: 5.0e5 | ||
|
||
3DBallHardLearning: | ||
normalize: true | ||
batch_size: 256 | ||
summary_freq: 1000 | ||
time_horizon: 1000 | ||
max_steps: 5.0e5 | ||
|
||
TennisLearning: | ||
normalize: true | ||
max_steps: 2e5 | ||
|
||
CrawlerStaticLearning: | ||
normalize: true | ||
time_horizon: 1000 | ||
batch_size: 256 | ||
train_interval: 3 | ||
buffer_size: 500000 | ||
buffer_init_steps: 2000 | ||
max_steps: 5e5 | ||
summary_freq: 3000 | ||
init_entcoef: 1.0 | ||
num_layers: 3 | ||
hidden_units: 512 | ||
|
||
CrawlerDynamicLearning: | ||
normalize: true | ||
time_horizon: 1000 | ||
batch_size: 256 | ||
buffer_size: 500000 | ||
summary_freq: 3000 | ||
train_interval: 3 | ||
num_layers: 3 | ||
max_steps: 5e5 | ||
hidden_units: 512 | ||
|
||
WalkerLearning: | ||
normalize: true | ||
time_horizon: 1000 | ||
batch_size: 256 | ||
buffer_size: 500000 | ||
max_steps: 2e6 | ||
summary_freq: 3000 | ||
num_layers: 3 | ||
train_interval: 3 | ||
hidden_units: 512 | ||
reward_signals: | ||
extrinsic: | ||
strength: 1.0 | ||
gamma: 0.995 | ||
|
||
ReacherLearning: | ||
normalize: true | ||
time_horizon: 1000 | ||
batch_size: 128 | ||
buffer_size: 500000 | ||
max_steps: 1e6 | ||
summary_freq: 3000 | ||
|
||
HallwayLearning: | ||
use_recurrent: true | ||
sequence_length: 32 | ||
num_layers: 2 | ||
hidden_units: 128 | ||
memory_size: 256 | ||
beta: 0.0 | ||
init_entcoef: 0.1 | ||
max_steps: 5.0e5 | ||
summary_freq: 1000 | ||
time_horizon: 64 | ||
use_recurrent: true | ||
|
||
VisualHallwayLearning: | ||
use_recurrent: true | ||
sequence_length: 32 | ||
num_layers: 1 | ||
hidden_units: 128 | ||
memory_size: 256 | ||
beta: 1.0e-2 | ||
gamma: 0.99 | ||
batch_size: 64 | ||
max_steps: 5.0e5 | ||
summary_freq: 1000 | ||
time_horizon: 64 | ||
use_recurrent: true | ||
|
||
VisualPushBlockLearning: | ||
use_recurrent: true | ||
sequence_length: 32 | ||
num_layers: 1 | ||
hidden_units: 128 | ||
memory_size: 256 | ||
beta: 1.0e-2 | ||
gamma: 0.99 | ||
buffer_size: 1024 | ||
batch_size: 64 | ||
max_steps: 5.0e5 | ||
summary_freq: 1000 | ||
time_horizon: 64 | ||
|
||
GridWorldLearning: | ||
batch_size: 128 | ||
normalize: false | ||
num_layers: 1 | ||
hidden_units: 128 | ||
init_entcoef: 0.01 | ||
buffer_size: 50000 | ||
max_steps: 5.0e5 | ||
summary_freq: 2000 | ||
time_horizon: 5 | ||
reward_signals: | ||
extrinsic: | ||
strength: 1.0 | ||
gamma: 0.9 | ||
|
||
BasicLearning: | ||
batch_size: 64 | ||
normalize: false | ||
num_layers: 2 | ||
init_entcoef: 0.01 | ||
hidden_units: 20 | ||
max_steps: 5.0e5 | ||
summary_freq: 2000 | ||
time_horizon: 10 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.