-
Notifications
You must be signed in to change notification settings - Fork 0
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
merge latest #1
merge latest #1
Commits on Aug 30, 2018
-
Update snakecase to camelcase for certain variables.
PiperOrigin-RevId: 210592195
Configuration menu - View commit details
-
Copy full SHA for c154865 - Browse repository at this point
Copy the full SHA c154865View commit details -
Fix docstring, as it is not returning
is_episode_over
.PiperOrigin-RevId: 210983763
Configuration menu - View commit details
-
Copy full SHA for 37fa491 - Browse repository at this point
Copy the full SHA 37fa491View commit details
Commits on Sep 3, 2018
-
BEGIN: Add "apt-get update" to install instructions.
PiperOrigin-RevId: 211382454
Configuration menu - View commit details
-
Copy full SHA for e97a3cd - Browse repository at this point
Copy the full SHA e97a3cdView commit details
Commits on Sep 4, 2018
-
Configuration menu - View commit details
-
Copy full SHA for 98ef0f5 - Browse repository at this point
Copy the full SHA 98ef0f5View commit details
Commits on Sep 7, 2018
-
Add Machado et al. reference to main README, and update some referenc…
…es to their published links. PiperOrigin-RevId: 211953206
Configuration menu - View commit details
-
Copy full SHA for 2664814 - Browse repository at this point
Copy the full SHA 2664814View commit details
Commits on Sep 13, 2018
-
Update install instructions for tensorflow with GPU support.
PiperOrigin-RevId: 212782732
Configuration menu - View commit details
-
Copy full SHA for 46222d7 - Browse repository at this point
Copy the full SHA 46222d7View commit details
Commits on Sep 18, 2018
-
Add support for in-iteration Tensorboard reporting.
PiperOrigin-RevId: 213423885
Configuration menu - View commit details
-
Copy full SHA for fb3f376 - Browse repository at this point
Copy the full SHA fb3f376View commit details -
Add a What's New section to the main README and include the latest in…
…-iteration change. PiperOrigin-RevId: 213449527
Configuration menu - View commit details
-
Copy full SHA for a59d5d6 - Browse repository at this point
Copy the full SHA a59d5d6View commit details
Commits on Sep 28, 2018
-
Configuration menu - View commit details
-
Copy full SHA for 11b435f - Browse repository at this point
Copy the full SHA 11b435fView commit details -
Removed redundant target q-value computation and added option for dou…
…ble dqn. PiperOrigin-RevId: 213507746
Configuration menu - View commit details
-
Copy full SHA for 7d7828d - Browse repository at this point
Copy the full SHA 7d7828dView commit details -
Add visibility for IQN double-DQN functionality to the README.
PiperOrigin-RevId: 213597916
Configuration menu - View commit details
-
Copy full SHA for 70b81a1 - Browse repository at this point
Copy the full SHA 70b81a1View commit details -
Observation shape can be a tuple, Circular memory buffer's logging sh…
…ould allow for this. PiperOrigin-RevId: 213686185
Configuration menu - View commit details
-
Copy full SHA for 94e1850 - Browse repository at this point
Copy the full SHA 94e1850View commit details -
Configuration menu - View commit details
-
Copy full SHA for aaf334b - Browse repository at this point
Copy the full SHA aaf334bView commit details -
Fixed quantile reshaping bug and set
terminal_on_life_loss = True
f……or the ICML gin config file. PiperOrigin-RevId: 214080101
Configuration menu - View commit details
-
Copy full SHA for 2de70a4 - Browse repository at this point
Copy the full SHA 2de70a4View commit details
Commits on Oct 16, 2018
-
Update JSON files, links and colab utils to use the IQN runs after th…
…e bug-fix. PiperOrigin-RevId: 217402619
Configuration menu - View commit details
-
Copy full SHA for 29661e3 - Browse repository at this point
Copy the full SHA 29661e3View commit details
Commits on Oct 17, 2018
-
Configuration menu - View commit details
-
Copy full SHA for 5259379 - Browse repository at this point
Copy the full SHA 5259379View commit details
Commits on Oct 29, 2018
-
update the assertion clause in Runner
PiperOrigin-RevId: 218741713
Configuration menu - View commit details
-
Copy full SHA for 38b1fd2 - Browse repository at this point
Copy the full SHA 38b1fd2View commit details -
Provide the graph definition to Tensorboard.
PiperOrigin-RevId: 219163382
Configuration menu - View commit details
-
Copy full SHA for 4be166d - Browse repository at this point
Copy the full SHA 4be166dView commit details
Commits on Nov 1, 2018
-
Add download links for each of the individual checkpoints, to avoid h…
…aving to download all of them as a single .tar.gz file. PiperOrigin-RevId: 219607104
Configuration menu - View commit details
-
Copy full SHA for 6665652 - Browse repository at this point
Copy the full SHA 6665652View commit details
Commits on Nov 2, 2018
-
Configuration menu - View commit details
-
Copy full SHA for e5d8465 - Browse repository at this point
Copy the full SHA e5d8465View commit details
Commits on Nov 9, 2018
-
Configuration menu - View commit details
-
Copy full SHA for 7a58561 - Browse repository at this point
Copy the full SHA 7a58561View commit details
Commits on Nov 13, 2018
-
Configuration menu - View commit details
-
Copy full SHA for 688a7e2 - Browse repository at this point
Copy the full SHA 688a7e2View commit details -
PiperOrigin-RevId: 220686551
Configuration menu - View commit details
-
Copy full SHA for 7ca1f2d - Browse repository at this point
Copy the full SHA 7ca1f2dView commit details -
Configuration menu - View commit details
-
Copy full SHA for bea54bb - Browse repository at this point
Copy the full SHA bea54bbView commit details -
Generalize agent constructors to accept different specifications of o…
…bservation shape/type, and the stack size. PiperOrigin-RevId: 221138027
Configuration menu - View commit details
-
Copy full SHA for 8d6cbb3 - Browse repository at this point
Copy the full SHA 8d6cbb3View commit details -
Add a thin wrapper around Gym environments to make them conformant to…
… the API expected by Dopamine. PiperOrigin-RevId: 221243592
Configuration menu - View commit details
-
Copy full SHA for 292f797 - Browse repository at this point
Copy the full SHA 292f797View commit details -
Configuration menu - View commit details
-
Copy full SHA for 4eec4a8 - Browse repository at this point
Copy the full SHA 4eec4a8View commit details -
Configuration menu - View commit details
-
Copy full SHA for 32d23e1 - Browse repository at this point
Copy the full SHA 32d23e1View commit details
Commits on Nov 14, 2018
-
Remove TF dependency in setup and increase version number.
PiperOrigin-RevId: 221502319
Configuration menu - View commit details
-
Copy full SHA for 1f54124 - Browse repository at this point
Copy the full SHA 1f54124View commit details
Commits on Nov 16, 2018
-
Generalize observation_shape specification, to allow for non-square s…
…hapes. PiperOrigin-RevId: 221709966
Configuration menu - View commit details
-
Copy full SHA for 0d9afcf - Browse repository at this point
Copy the full SHA 0d9afcfView commit details
Commits on Nov 19, 2018
-
Increase version number for a new PyPi release.
PiperOrigin-RevId: 222120861
Configuration menu - View commit details
-
Copy full SHA for 06d64fc - Browse repository at this point
Copy the full SHA 06d64fcView commit details
Commits on Nov 22, 2018
-
Fix the handling of custom observation shapes and types. This include…
…s enforcing shapes to be passed in as tuples. PiperOrigin-RevId: 222560771
Configuration menu - View commit details
-
Copy full SHA for bc66570 - Browse repository at this point
Copy the full SHA bc66570View commit details
Commits on Jan 4, 2019
-
Configuration menu - View commit details
-
Copy full SHA for b4341f9 - Browse repository at this point
Copy the full SHA b4341f9View commit details
Commits on Jan 31, 2019
-
Refactor atari.run_experiment into common.run_experiment to enable su…
…pport for non-Atari Gym environments. PiperOrigin-RevId: 224811437
Configuration menu - View commit details
-
Copy full SHA for 584dd30 - Browse repository at this point
Copy the full SHA 584dd30View commit details -
Refactor atari.run_experiment into common.run_experiment to enable su…
…pport for non-Atari Gym environments. PiperOrigin-RevId: 224819061
Configuration menu - View commit details
-
Copy full SHA for 163a9c0 - Browse repository at this point
Copy the full SHA 163a9c0View commit details -
Adding missing life loss parameter to some baseline configuration fil…
…es. Changing the IQN learning rate and Adam epsilon in the "apples to apples" comparison configuration as the algorithm seems unstable with the smaller Rainbow epsilon. PiperOrigin-RevId: 225007621
Configuration menu - View commit details
-
Copy full SHA for d5f7db7 - Browse repository at this point
Copy the full SHA d5f7db7View commit details -
Refactor atari.run_experiment into common.run_experiment to enable su…
…pport for non-Atari Gym environments. PiperOrigin-RevId: 225040877
Configuration menu - View commit details
-
Copy full SHA for 31799e9 - Browse repository at this point
Copy the full SHA 31799e9View commit details -
Fix observation_dtype argument in WrappedPrioritizedReplayBuffer whic…
…h wasn't getting passed along. PiperOrigin-RevId: 225234742
Configuration menu - View commit details
-
Copy full SHA for ce1086e - Browse repository at this point
Copy the full SHA ce1086eView commit details -
Refactor network specifications into discrete_domains.atari_lib and a…
…dd an initial network for Cartpole DQN. PiperOrigin-RevId: 225351561
Configuration menu - View commit details
-
Copy full SHA for a53ff8a - Browse repository at this point
Copy the full SHA a53ff8aView commit details -
Configuration menu - View commit details
-
Copy full SHA for 09080db - Browse repository at this point
Copy the full SHA 09080dbView commit details -
Make the identity_epsilon function conform to the existing linearly_d…
…ecaying epsilon function. PiperOrigin-RevId: 225414171
Configuration menu - View commit details
-
Copy full SHA for 4b8a6f6 - Browse repository at this point
Copy the full SHA 4b8a6f6View commit details -
Configuration menu - View commit details
-
Copy full SHA for 6f6a638 - Browse repository at this point
Copy the full SHA 6f6a638View commit details -
Configuration menu - View commit details
-
Copy full SHA for d69f3c9 - Browse repository at this point
Copy the full SHA d69f3c9View commit details -
Add BibTeX entry for Dopamine white paper.
PiperOrigin-RevId: 227857505
Configuration menu - View commit details
-
Copy full SHA for d4acd20 - Browse repository at this point
Copy the full SHA d4acd20View commit details -
Refactor dopamine circular and prioritized replay buffer to support v…
…ectorized action and rewards and also add next action to storage. PiperOrigin-RevId: 227942879
Configuration menu - View commit details
-
Copy full SHA for cb1e248 - Browse repository at this point
Copy the full SHA cb1e248View commit details -
Some minor fixes for prioritized_replay_buffer.py and related files.
PiperOrigin-RevId: 228429755
Configuration menu - View commit details
-
Copy full SHA for da6bbc7 - Browse repository at this point
Copy the full SHA da6bbc7View commit details -
This CL ensures that RainbowAgent.__init__ always calls the right fun…
…ction with an explicit call to dqn_agent.DQNAgent.__init__ PiperOrigin-RevId: 228805979
Configuration menu - View commit details
-
Copy full SHA for 87b5eef - Browse repository at this point
Copy the full SHA 87b5eefView commit details -
Add rainbow support for cartpole and acrobot.
PiperOrigin-RevId: 230914146
Configuration menu - View commit details
-
Copy full SHA for 206c57d - Browse repository at this point
Copy the full SHA 206c57dView commit details -
Finish migration of Dopamine to using discrete_domains instead of atari.
PiperOrigin-RevId: 231432169
Configuration menu - View commit details
-
Copy full SHA for 034e0ab - Browse repository at this point
Copy the full SHA 034e0abView commit details -
Configuration menu - View commit details
-
Copy full SHA for eb4b102 - Browse repository at this point
Copy the full SHA eb4b102View commit details -
Fix the the dopamine circular_replay_buffer for case in which reward …
…is a vector PiperOrigin-RevId: 231540267
Configuration menu - View commit details
-
Copy full SHA for b658c5e - Browse repository at this point
Copy the full SHA b658c5eView commit details -
Set reasonable default settings for rainbow on cartpole and acrobot.
PiperOrigin-RevId: 231598699
Configuration menu - View commit details
-
Copy full SHA for f3653b5 - Browse repository at this point
Copy the full SHA f3653b5View commit details -
Configuration menu - View commit details
-
Copy full SHA for 19b0348 - Browse repository at this point
Copy the full SHA 19b0348View commit details -
Configuration menu - View commit details
-
Copy full SHA for 11dee79 - Browse repository at this point
Copy the full SHA 11dee79View commit details
Commits on Feb 2, 2019
-
Add agents using Fourier basis and linear Q function approximation
PiperOrigin-RevId: 232039653
Configuration menu - View commit details
-
Copy full SHA for 202fa9e - Browse repository at this point
Copy the full SHA 202fa9eView commit details -
Adding a colab demonstrating how to train agents on Cartpole.
PiperOrigin-RevId: 232073385
Configuration menu - View commit details
-
Copy full SHA for 9dbd94a - Browse repository at this point
Copy the full SHA 9dbd94aView commit details -
Remove unused
debug_mode
flag and update documentation.PiperOrigin-RevId: 232074103
Configuration menu - View commit details
-
Copy full SHA for 753a243 - Browse repository at this point
Copy the full SHA 753a243View commit details
Commits on Feb 5, 2019
-
removed the comment regarding the time limit, as it's wrong
PiperOrigin-RevId: 232499569
Configuration menu - View commit details
-
Copy full SHA for e873d7c - Browse repository at this point
Copy the full SHA e873d7cView commit details -
Remove atari-py and cmake installs for cartpole colab.
PiperOrigin-RevId: 232524026
Configuration menu - View commit details
-
Copy full SHA for 5fad7e9 - Browse repository at this point
Copy the full SHA 5fad7e9View commit details -
Make default number of checkpoints saved consistent between dqn_agent…
… and checkpointer. PiperOrigin-RevId: 232544723
Configuration menu - View commit details
-
Copy full SHA for 53d3450 - Browse repository at this point
Copy the full SHA 53d3450View commit details -
Configuration menu - View commit details
-
Copy full SHA for 4799c3a - Browse repository at this point
Copy the full SHA 4799c3aView commit details
Commits on Feb 7, 2019
-
Update Cartpole configuration files and colab to match default Gym ma…
…x episode length. PiperOrigin-RevId: 232791515
Configuration menu - View commit details
-
Copy full SHA for 79b024f - Browse repository at this point
Copy the full SHA 79b024fView commit details
Commits on Feb 8, 2019
-
Update the agents colab to the new Dopamine 2.0 interface.
PiperOrigin-RevId: 233077734
Configuration menu - View commit details
-
Copy full SHA for d7049fe - Browse repository at this point
Copy the full SHA d7049feView commit details
Commits on Feb 12, 2019
-
Configuration menu - View commit details
-
Copy full SHA for 349261c - Browse repository at this point
Copy the full SHA 349261cView commit details
Commits on Feb 15, 2019
-
Update documentation to support Python 3.6.
PiperOrigin-RevId: 234139600
Configuration menu - View commit details
-
Copy full SHA for 0ce0709 - Browse repository at this point
Copy the full SHA 0ce0709View commit details -
Update
create_agent
docstring.PiperOrigin-RevId: 234151608
Configuration menu - View commit details
-
Copy full SHA for 711e188 - Browse repository at this point
Copy the full SHA 711e188View commit details
Commits on Apr 11, 2019
-
Add close method to AtariPreprocessing.
PiperOrigin-RevId: 235068759
Configuration menu - View commit details
-
Copy full SHA for 00a5b32 - Browse repository at this point
Copy the full SHA 00a5b32View commit details -
Adding a comment to clarify why Rainbow uses the same data structure …
…for both replay schemes PiperOrigin-RevId: 237079830
Configuration menu - View commit details
-
Copy full SHA for 33c4f61 - Browse repository at this point
Copy the full SHA 33c4f61View commit details -
Update DQNAgent's eval_mode. Allow setting it in constructor and remo…
…ve it from the bundle. PiperOrigin-RevId: 238107489
Configuration menu - View commit details
-
Copy full SHA for 2639e7d - Browse repository at this point
Copy the full SHA 2639e7dView commit details -
Remove unused dependency on tf.slim in agents
PiperOrigin-RevId: 238608544
Configuration menu - View commit details
-
Copy full SHA for 75fc33a - Browse repository at this point
Copy the full SHA 75fc33aView commit details -
Changing CartPole/Acrobot observation type to match what is returned …
…by Gym PiperOrigin-RevId: 241769847
Configuration menu - View commit details
-
Copy full SHA for f6dc339 - Browse repository at this point
Copy the full SHA f6dc339View commit details -
Fix bug whereby batches of size larger than 1000 would never get
PiperOrigin-RevId: 242851617
Configuration menu - View commit details
-
Copy full SHA for 2435916 - Browse repository at this point
Copy the full SHA 2435916View commit details
Commits on Apr 16, 2019
-
Propagating observation dtype to the replay buffer in RainbowAgent si…
…milarly to DQNAgent. PiperOrigin-RevId: 243108947
Configuration menu - View commit details
-
Copy full SHA for 2ce82ea - Browse repository at this point
Copy the full SHA 2ce82eaView commit details -
Fix ValueError issue when reloading baselines and increase minor vers…
…ion number for new release. PiperOrigin-RevId: 243803145
Configuration menu - View commit details
-
Copy full SHA for 834c4b8 - Browse repository at this point
Copy the full SHA 834c4b8View commit details
Commits on Apr 17, 2019
-
Fix remaining instance of ValueError when numerics not cast as float6…
…4s, and increase minor version number for new release. PiperOrigin-RevId: 243966695
Configuration menu - View commit details
-
Copy full SHA for 01abb82 - Browse repository at this point
Copy the full SHA 01abb82View commit details
Commits on Apr 23, 2019
-
Only load training runs, as the colab uses TrainRunner, which doesn't…
… generate eval curves. PiperOrigin-RevId: 244255414
Configuration menu - View commit details
-
Copy full SHA for 826f172 - Browse repository at this point
Copy the full SHA 826f172View commit details