hiro/ray
1
0
Fork 0
mirror of https://github.com/vale981/ray synced 2025-03-11 21:56:39 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions
ray/rllib/tests
History
Sven Mika 5ac5ac9560
[RLlib] Fix broken example: tf-eager with custom-RNN (#6732). (#7021) 
* WIP.

* Fix float32 conversion in OneHot preprocessor (would cause float64 in eager, then NN-matmul-failure).
Add proper seq-len + state-in construction in eager_tf_policy.py::_compute_gradients().

* LINT.

* eager_tf_policy.py: Only set samples["seq_lens"] if RNN. Otherwise, eager-tracing will throw flattened-dict key-mismatch error.

* Move issue code to examples folder.

Co-authored-by: Eric Liang <ekhliang@gmail.com>
2020-02-06 09:44:08 -08:00
..
data/cartpole_small [rllib] Try moving RLlib to top level dir (#5324) 2019-08-05 23:25:49 -07:00
__init__.py [rllib] Try moving RLlib to top level dir (#5324) 2019-08-05 23:25:49 -07:00
mock_worker.py Remove future imports (#6724) 2020-01-09 00:15:48 -08:00
multiagent_pendulum.py Remove future imports (#6724) 2020-01-09 00:15:48 -08:00
run_regression_tests.py [rllib] Try moving RLlib to top level dir (#5324) 2019-08-05 23:25:49 -07:00
test_avail_actions_qmix.py Remove future imports (#6724) 2020-01-09 00:15:48 -08:00
test_catalog.py Remove (object) from class declarations. (#6658) 2020-01-02 17:42:13 -08:00
test_checkpoint_restore.py Remove future imports (#6724) 2020-01-09 00:15:48 -08:00
test_dependency.py Remove future imports (#6724) 2020-01-09 00:15:48 -08:00
test_eager_support.py [RLlib] Fix broken example: tf-eager with custom-RNN (#6732). (#7021) 2020-02-06 09:44:08 -08:00
test_env_with_subprocess.py [RLlib] Implement PPO torch version. (#6826) 2020-01-20 23:06:50 -08:00
test_evaluators.py Remove future imports (#6724) 2020-01-09 00:15:48 -08:00
test_external_env.py Remove future imports (#6724) 2020-01-09 00:15:48 -08:00
test_external_multi_agent_env.py Remove future imports (#6724) 2020-01-09 00:15:48 -08:00
test_filters.py Remove future imports (#6724) 2020-01-09 00:15:48 -08:00
test_ignore_worker_failure.py Remove future imports (#6724) 2020-01-09 00:15:48 -08:00
test_io.py Remove future imports (#6724) 2020-01-09 00:15:48 -08:00
test_local.py Remove future imports (#6724) 2020-01-09 00:15:48 -08:00
test_lstm.py Remove future imports (#6724) 2020-01-09 00:15:48 -08:00
test_multi_agent_env.py [RLlib] Implement PPO torch version. (#6826) 2020-01-20 23:06:50 -08:00
test_nested_spaces.py Remove future imports (#6724) 2020-01-09 00:15:48 -08:00
test_optimizers.py [RLlib] Implement PPO torch version. (#6826) 2020-01-20 23:06:50 -08:00
test_perf.py Remove future imports (#6724) 2020-01-09 00:15:48 -08:00
test_reproducibility.py Remove future imports (#6724) 2020-01-09 00:15:48 -08:00
test_rollout.sh [rllib] Rollout extensions (#6065) 2019-11-05 20:34:18 -08:00
test_rollout_worker.py [rllib] implemented compute_advantages without gae (#6941) 2020-01-31 22:25:45 -08:00
test_supported_spaces.py [rllib] RLlib chooses wrong neural network model for Atari in 0.7.5 (#6087) 2019-11-05 11:36:29 -08:00