Home
Projects
Resources
Alternatives
Blog
Sign In
Keras Rl Versions
Save
Deep Reinforcement Learning for Keras.
Overview
Versions
Reviews
Resources
v0.4.2
6 years ago
Fix Tensorboard support
Improve documentation
V0.4.1
6 years ago
Add support for current version of Keras and Gym
v0.4.0
6 years ago
Removes legacy code and now requires
Keras >= 2.0.7
(
https://github.com/matthiasplappert/keras-rl/pull/157
)
Adds two new policies (
https://github.com/matthiasplappert/keras-rl/pull/156
,
https://github.com/matthiasplappert/keras-rl/pull/122
)
Fixes a few problems with replay memory sampling being incorrect for certain edge cases (
https://github.com/matthiasplappert/keras-rl/pull/138
)
Fixes a problem with dropout in actor model for DDPG (
https://github.com/matthiasplappert/keras-rl/pull/150
)
v0.3.1
6 years ago
Require Keras < 2.0.7 due to non-trivial and breaking API change in optimizer code
v0.3.0
7 years ago
Full compatibility with the recently released Keras 2
New
SarsaAgent
implementation
New
train_policy
on
DQNAgent
and
SarsaAgent
to allow for different policies at training and test time
Minor clean-ups
v0.2.2
7 years ago
Fix version mix-up on release, otherwise identical to version
v0.2.1
v0.2.1
7 years ago
Add Dueling DQN
Add support for TensorFlow 1.0
Fix problem with default policy if multiple DQN agents are used simultaneously
v0.2.0rc1
7 years ago
Home
Projects
Resources
Alternatives
Blog
Sign In
Sign In to OSA
I agree with
Terms of Service
and
Privacy Policy
Sign In with Github