wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-08-11 11:24:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

[RLlib] DDPG PyTorch version. (#7953)

Browse Source 
The DDPG/TD3 algorithms currently do not have a PyTorch implementation. This PR adds PyTorch support for DDPG/TD3 to RLlib.
This PR:
- Depends on the re-factor PR for DDPG (Functional Algorithm API).
- Adds learning regression tests for the PyTorch version of DDPG and a DDPG (torch)
- Updates the documentation to reflect that DDPG and TD3 now support PyTorch.

* Learning Pendulum-v0 on torch version (same config as tf). Wall time a little slower (~20% than tf).
* Fix GPU target model problem.
This commit is contained in:
Sven Mika
2020-04-16 10:20:01 +02:00
committed by GitHub
parent e1d3f7eba6
commit d0fab84e4d
21 changed files with 1016 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files
rllib/utils/framework.py
+3 -1
View File
@@ -192,7 +192,9 @@ def get_variable(value,
tf_name, initializer=value, dtype=dtype, trainable=trainable)
elif framework == "torch" and torch_tensor is True:
torch, _ = try_import_torch()
var_ = torch.from_numpy(value).to(device)
var_ = torch.from_numpy(value)
if device:
var_ = var_.to(device)
var_.requires_grad = trainable
return var_
# torch or None: Return python primitive.