Sven Mika
d8a081a185
[RLlib] Unity3D integration (n Unity3D clients vs learning server). ( #8590 )
2020-05-30 22:48:34 +02:00
Eric Liang
f48da50e1c
[rllib] observation function api for multi-agent ( #8236 )
2020-05-04 22:13:49 -07:00
Eric Liang
5cebee68d6
[rllib] Add scaling guide to documentation, improve bandit docs ( #7780 )
...
* update
* reword
* update
* ms
* multi node sgd
* reorder
* improve bandit docs
* contrib
* update
* ref
* improve refs
* fix build
* add pillow dep
* add pil
* update pil
* pillow
* remove false
2020-03-27 22:05:43 -07:00
hubcity
3d0a8662b3
#7246 - Fixing broken links ( #7247 )
...
* #7246 - Fixing broken links
* Apply suggestions from code review
Co-authored-by: Richard Liaw <rliaw@berkeley.edu>
2020-03-25 21:46:13 -07:00
Eric Liang
9392cdbf74
[rllib] Add high-performance external application connector ( #7641 )
2020-03-20 12:43:57 -07:00
Eric Liang
dd70720578
[rllib] Rename sample_batch_size => rollout_fragment_length ( #7503 )
...
* bulk rename
* deprecation warn
* update doc
* update fig
* line length
* rename
* make pytest comptaible
* fix test
* fi sys
* rename
* wip
* fix more
* lint
* update svg
* comments
* lint
* fix use of batch steps
2020-03-14 12:05:04 -07:00
Sven Mika
510c850651
[RLlib] SAC add discrete action support. ( #7320 )
...
* Exploration API (+EpsilonGreedy sub-class).
* Exploration API (+EpsilonGreedy sub-class).
* Cleanup/LINT.
* Add `deterministic` to generic Trainer config (NOTE: this is still ignored by most Agents).
* Add `error` option to deprecation_warning().
* WIP.
* Bug fix: Get exploration-info for tf framework.
Bug fix: Properly deprecate some DQN config keys.
* WIP.
* LINT.
* WIP.
* Split PerWorkerEpsilonGreedy out of EpsilonGreedy.
Docstrings.
* Fix bug in sampler.py in case Policy has self.exploration = None
* Update rllib/agents/dqn/dqn.py
Co-Authored-By: Eric Liang <ekhliang@gmail.com>
* WIP.
* Update rllib/agents/trainer.py
Co-Authored-By: Eric Liang <ekhliang@gmail.com>
* WIP.
* Change requests.
* LINT
* In tune/utils/util.py::deep_update() Only keep deep_updat'ing if both original and value are dicts. If value is not a dict, set
* Completely obsolete syn_replay_optimizer.py's parameters schedule_max_timesteps AND beta_annealing_fraction (replaced with prioritized_replay_beta_annealing_timesteps).
* Update rllib/evaluation/worker_set.py
Co-Authored-By: Eric Liang <ekhliang@gmail.com>
* Review fixes.
* Fix default value for DQN's exploration spec.
* LINT
* Fix recursion bug (wrong parent c'tor).
* Do not pass timestep to get_exploration_info.
* Update tf_policy.py
* Fix some remaining issues with test cases and remove more deprecated DQN/APEX exploration configs.
* Bug fix tf-action-dist
* DDPG incompatibility bug fix with new DQN exploration handling (which is imported by DDPG).
* Switch off exploration when getting action probs from off-policy-estimator's policy.
* LINT
* Fix test_checkpoint_restore.py.
* Deprecate all SAC exploration (unused) configs.
* Properly use `model.last_output()` everywhere. Instead of `model._last_output`.
* WIP.
* Take out set_epsilon from multi-agent-env test (not needed, decays anyway).
* WIP.
* Trigger re-test (flaky checkpoint-restore test).
* WIP.
* WIP.
* Add test case for deterministic action sampling in PPO.
* bug fix.
* Added deterministic test cases for different Agents.
* Fix problem with TupleActions in dynamic-tf-policy.
* Separate supported_spaces tests so they can be run separately for easier debugging.
* LINT.
* Fix autoregressive_action_dist.py test case.
* Re-test.
* Fix.
* Remove duplicate py_test rule from bazel.
* LINT.
* WIP.
* WIP.
* SAC fix.
* SAC fix.
* WIP.
* WIP.
* WIP.
* FIX 2 examples tests.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* Fix.
* LINT.
* Renamed test file.
* WIP.
* Add unittest.main.
* Make action_dist_class mandatory.
* fix
* FIX.
* WIP.
* WIP.
* Fix.
* Fix.
* Fix explorations test case (contextlib cannot find its own nullcontext??).
* Force torch to be installed for QMIX.
* LINT.
* Fix determine_tests_to_run.py.
* Fix determine_tests_to_run.py.
* WIP
* Add Random exploration component to tests (fixed issue with "static-graph randomness" via py_function).
* Add Random exploration component to tests (fixed issue with "static-graph randomness" via py_function).
* Rename some stuff.
* Rename some stuff.
* WIP.
* update.
* WIP.
* Gumbel Softmax Dist.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP.
* WIP
* WIP.
* WIP.
* Hypertune.
* Hypertune.
* Hypertune.
* Lock-in.
* Cleanup.
* LINT.
* Fix.
* Update rllib/policy/eager_tf_policy.py
Co-Authored-By: Kristian Hartikainen <kristian.hartikainen@gmail.com>
* Update rllib/agents/sac/sac_policy.py
Co-Authored-By: Kristian Hartikainen <kristian.hartikainen@gmail.com>
* Update rllib/agents/sac/sac_policy.py
Co-Authored-By: Kristian Hartikainen <kristian.hartikainen@gmail.com>
* Update rllib/models/tf/tf_action_dist.py
Co-Authored-By: Kristian Hartikainen <kristian.hartikainen@gmail.com>
* Update rllib/models/tf/tf_action_dist.py
Co-Authored-By: Kristian Hartikainen <kristian.hartikainen@gmail.com>
* Fix items from review comments.
* Add dm_tree to RLlib dependencies.
* Add dm_tree to RLlib dependencies.
* Fix DQN test cases ((Torch)Categorical).
* Fix wrong pip install.
Co-authored-by: Eric Liang <ekhliang@gmail.com>
Co-authored-by: Kristian Hartikainen <kristian.hartikainen@gmail.com>
2020-03-06 10:37:12 -08:00
Eric Liang
249ca2cf9e
[rllib] add blog posts to examples list ( #5762 )
...
* add blog post
* remove
* link
2019-09-23 10:42:21 -07:00
gehring
b520f6141e
[rllib] Adds eager support with a generic TFEagerPolicy class ( #5436 )
2019-08-23 14:21:11 +08:00
Eric Liang
a1d2e17623
[rllib] Autoregressive action distributions ( #5304 )
2019-08-10 14:05:12 -07:00
Eric Liang
592f313210
[rllib] Centralized critic / PPO example on TwoStepGame ( #5392 )
2019-08-08 14:03:28 -07:00
Eric Liang
5d7afe8092
[rllib] Try moving RLlib to top level dir ( #5324 )
2019-08-05 23:25:49 -07:00
Kristian Hartikainen
13fb9fe3db
[rllib] Feature/soft actor critic v2 ( #5328 )
...
* Add base for Soft Actor-Critic
* Pick changes from old SAC branch
* Update sac.py
* First implementation of sac model
* Remove unnecessary SAC imports
* Prune unnecessary noise and exploration code
* Implement SAC model and use that in SAC policy
* runs but doesn't learn
* clear state
* fix batch size
* Add missing alpha grads and vars
* -200 by 2k timesteps
* doc
* lazy squash
* one file
* ignore tfp
* revert done
2019-08-01 23:37:36 -07:00
Eric Liang
20450a4e82
[rllib] Add rock paper scissors multi-agent example ( #5336 )
2019-08-01 13:03:59 -07:00
Eric Liang
a45c61e19b
[rllib] Update concepts docs and add "Building Policies in Torch/TensorFlow" section ( #4821 )
...
* wip
* fix index
* fix bugs
* todo
* add imports
* note on get ph
* note on get ph
* rename to building custom algs
* add rnn state info
2019-05-27 14:17:32 -07:00
Eric Liang
02583a8598
[rllib] Rename PolicyGraph => Policy, move from evaluation/ to policy/ ( #4819 )
...
This implements some of the renames proposed in #4813
We leave behind backwards-compatibility aliases for *PolicyGraph and SampleBatch.
2019-05-20 16:46:05 -07:00
Eric Liang
3807fb505b
[rllib] TensorFlow 2 compatibility ( #4802 )
2019-05-16 22:12:07 -07:00
Eric Liang
7d5ef6d99c
[rllib] Support continuous action distributions in IMPALA/APPO ( #4771 )
2019-05-16 22:05:07 -07:00
Eric Liang
37208216ae
[rllib] Rename Agent to Trainer ( #4556 )
2019-04-07 00:36:18 -07:00
bjg2
77005d1814
[rllib] Make batch timeout for remote workers tunable ( #4435 )
2019-03-29 13:19:42 -07:00
Eric Liang
5b8eb475ce
[rllib] Allow None to be specified in multi-agent envs ( #4464 )
...
* wip
* check
* doc update
* Update hierarchical_training.py
2019-03-25 11:38:17 -07:00
Eric Liang
c7f74dbdc7
[rllib] Add async remote workers ( #4253 )
2019-03-08 15:39:48 -08:00
Eric Liang
d9da183c7d
[rllib] Custom supervised loss API ( #4083 )
2019-02-24 15:36:13 -08:00
Eric Liang
f8bef004da
[rllib] Improve error message for bad envs, add remote env docs ( #4044 )
...
* commit
* fix up rew
2019-02-18 01:28:19 -08:00
Eric Liang
fb73cedf70
[rllib] Add examples page, add hierarchical training example, delete SC2 examples ( #3815 )
...
* wip
* lint
* wip
* up
* wip
* update examples
* wip
* remove carla
* update
* improve envspec
* link to custom
* Update rllib-env.rst
* update
* fix
* fn
* lint
* ds
* ssd games
* desc
* fix up docs
* fix
2019-01-29 21:06:09 -08:00
Eric Liang
04ec47cbd4
[rllib] annotate public vs developer vs private APIs ( #3808 )
2019-01-23 21:27:26 -08:00
Michael Luo
16f7ca45e4
Appo ( #3779 )
...
* Deleted old fork, updated new ray and moved PPO-impala to APPO in ppo folder
* Deleted unneccesary vtrace.py file
* Update pong-impala.yaml
* Cleaned PPO Code
* Update pong-impala.yaml
* Update pong-impala.yaml
* wip
* new ifle
* refactor
* add vtrace off option
* revert
* support any space
* docs
* fix comment
* remove kl
* Update cartpole-appo-vtrace.yaml
2019-01-18 13:40:26 -08:00
Jones Wong
319c1340cb
[rllib] Develop MARWIL ( #3635 )
...
* add marvil policy graph
* fix typo
* add offline optimizer and enable running marwil
* fix loss function
* add maintaining the moving average of advantage norm
* use sync replay optimizer for unifying
* remove offline optimizer and use sync replay optimizer
* format by yapf
* add imitation learning objective
* fix according to eric's review
* format by yapf
* revise
* add test data
* marwil
2019-01-16 19:00:43 -08:00
Eric Liang
401e656b95
[rllib] Sync filters at end of iteration not start; hierarchical docs ( #3769 )
2019-01-15 16:25:25 -08:00
Eric Liang
ca864faece
[rllib] Documentation for I/O API and multi-agent support / cleanup ( #3650 )
2019-01-03 15:15:36 +08:00
Eric Liang
303883a3b6
[rllib] [rfc] add contrib module and guideline for merging ( #3565 )
...
This adds guidelines for merging code into `rllib/contrib` vs `rllib/agents`. Also, clean up the agent import code to make registration easier.
2018-12-20 10:44:34 -08:00
Eric Liang
db0dee573e
[rllib] Q-Mix implementation (Q-Mix, VDN, IQN, and Ape-X variants) ( #3548 )
2018-12-18 10:40:01 -08:00
Eric Liang
ce388a45cf
[rllib] Learner should not see clipped actions ( #3496 )
2018-12-09 21:57:11 -08:00
Eric Liang
d864f299d7
[rllib] fixes from dogfooding multi-agent ( #3456 )
...
auto wrap multi-agent dict and tuple spaces by keeping a policy -> preprocessor in the sampler
add some Q-learning debug stats
report min, max of custom metrics
better errors
2018-12-05 23:31:45 -08:00
Eric Liang
ce355d13d4
[rllib] Allow envs to be auto-registered; add on_train_result callback with curriculum example ( #3451 )
...
* train step and docs
* debug
* doc
* doc
* fix examples
* fix code
* integration test
* fix
* ...
* space
* instance
* Update .travis.yml
* fix test
2018-12-03 23:15:43 -08:00
Eric Liang
f0df97db6f
[rllib] example and docs on how to use parametric actions with DQN / PG algorithms ( #3384 )
2018-11-27 23:35:19 -08:00
Eric Liang
8b76bab25c
[rllib] docs for td3 ( #3381 )
...
* td3 doc
* Update rllib-env.rst
2018-11-22 13:36:47 -08:00
Eric Liang
bd0dbde149
[rllib] Rename ServingEnv => ExternalEnv ( #3302 )
2018-11-12 16:31:27 -08:00
Eric Liang
9dd3eedbac
[rllib] rollout.py should reduce num workers ( #3263 )
...
## What do these changes do?
Don't create an excessive amount of workers for rollout.py, and also fix up the env wrapping to be consistent with the internal agent wrapper.
## Related issue number
Closes #3260 .
2018-11-09 12:29:16 -08:00
Eric Liang
369cb833fe
[rllib] Implement custom metrics ( #3144 )
2018-11-03 18:48:32 -07:00
Eric Liang
cd284bb487
[rllib] Document env compatibility, Ape-X support for multi-agent ( #3147 )
2018-10-31 21:59:34 -07:00
Eric Liang
a221f55b0d
[rllib] Add custom value functions, fix up and document multi-agent variable sharing ( #3151 )
2018-10-29 19:37:27 -07:00
Eric Liang
b45bed4bce
[rllib] Propagate model options correctly in ARS / ES, to action dist of PPO ( #2974 )
...
* fix
* fix
* fix it
* propagate conf to action dist
* move carla example too
* rr
* Update policies.py
* wip
* lint
2018-10-01 12:49:39 -07:00
Philipp Moritz
4db196438b
fix 'from ray.rllib import ppo' in doc ( #2794 )
2018-08-31 23:34:47 -07:00
Eric Liang
fbe6c59f72
[rllib] Misc fixes, A2C ( #2679 )
...
A bunch of minor rllib fixes:
pull in latest baselines atari wrapper changes (and use deepmind wrapper by default)
move reward clipping to policy evaluator
add a2c variant of a3c
reduce vision network fc layer size to 256 units
switch to 84x84 images
doc tweaks
print timesteps in tune status
2018-08-20 15:28:03 -07:00
Eric Liang
9a479b3a63
[rllib] Document creating an ensemble of envs; also add vector_index attribute to env config ( #2513 )
...
This also removes the async resetting code in VectorEnv. While that improves benchmark performance slightly, it substantially complicates env configuration and probably isn't worth it for most envs.
This makes it easy to efficiently support setups like Joint PPO: https://s3-us-west-2.amazonaws.com/openai-assets/research-covers/retro-contest/gotta_learn_fast_report.pdf
For example, for 188 envs, you could do something like num_envs: 10, num_envs_per_worker: 19.
2018-08-01 16:29:27 -07:00
Eric Liang
68660453e4
[rllib] Better support and add two-trainer example for multiagent ( #2443 )
...
This adds a simple DQN+PPO example for multi-agent. We don't do anything fancy here, just syncing weights between two separate trainers. This potentially is wasting some compute, but is very simple to set up.
It might be nice to share experience collection between the top-level trainers in the future.
2018-07-22 05:09:25 -07:00
Eric Liang
b316afeb43
[rllib] Add debug info back to PPO and fix optimizer compatibility ( #2366 )
2018-07-12 19:22:46 +02:00
Eric Liang
4ef9d15315
[rllib] Add concepts section of docs ( #2373 )
...
This fills in the rllib concepts documentation.
2018-07-08 18:46:52 -07:00
Eric Liang
8aa56c12e6
[rllib] Document "v2" APIs ( #2316 )
...
* re
* wip
* wip
* a3c working
* torch support
* pg works
* lint
* rm v2
* consumer id
* clean up pg
* clean up more
* fix python 2.7
* tf session management
* docs
* dqn wip
* fix compile
* dqn
* apex runs
* up
* impotrs
* ddpg
* quotes
* fix tests
* fix last r
* fix tests
* lint
* pass checkpoint restore
* kwar
* nits
* policy graph
* fix yapf
* com
* class
* pyt
* vectorization
* update
* test cpe
* unit test
* fix ddpg2
* changes
* wip
* args
* faster test
* common
* fix
* add alg option
* batch mode and policy serving
* multi serving test
* todo
* wip
* serving test
* doc async env
* num envs
* comments
* thread
* remove init hook
* update
* fix ppo
* comments1
* fix
* updates
* add jenkins tests
* fix
* fix pytorch
* fix
* fixes
* fix a3c policy
* fix squeeze
* fix trunc on apex
* fix squeezing for real
* update
* remove horizon test for now
* multiagent wip
* update
* fix race condition
* fix ma
* t
* doc
* st
* wip
* example
* wip
* working
* cartpole
* wip
* batch wip
* fix bug
* make other_batches None default
* working
* debug
* nit
* warn
* comments
* fix ppo
* fix obs filter
* update
* wip
* tf
* update
* fix
* cleanup
* cleanup
* spacing
* model
* fix
* dqn
* fix ddpg
* doc
* keep names
* update
* fix
* com
* docs
* clarify model outputs
* Update torch_policy_graph.py
* fix obs filter
* pass thru worker index
* fix
* rename
* vlad torch comments
* fix log action
* debug name
* fix lstm
* remove unused ddpg net
* remove conv net
* revert lstm
* wip
* wip
* cast
* wip
* works
* fix a3c
* works
* lstm util test
* doc
* clean up
* update
* fix lstm check
* move to end
* fix sphinx
* fix cmd
* remove bad doc
* envs
* vec
* doc prep
* models
* rl
* alg
* up
* clarify
* copy
* async sa
* fix
* comments
* fix a3c conf
* tune lstm
* fix reshape
* fix
* back to 16
* tuned a3c update
* update
* tuned
* optional
* merge
* wip
* fix up
* move pg class
* rename env
* wip
* update
* tip
* alg
* readme
* fix catalog
* readme
* doc
* context
* remove prep
* comma
* add env
* link to paper
* paper
* update
* rnn
* update
* wip
* clean up ev creation
* fix
* fix
* fix
* fix lint
* up
* no comma
* ma
* Update run_multi_node_tests.sh
* fix
* sphinx is stupid
* sphinx is stupid
* clarify torch graph
* no horizon
* fix config
* sb
* Update test_optimizers.py
2018-07-01 00:05:08 -07:00
