gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2026-03-11 12:05:47 +01:00
Code Issues Projects Releases Wiki Activity

Adding mxnet components to rl_coach/architectures (#60)

Browse Source 
Adding mxnet components to rl_coach architectures.

- Supports PPO and DQN
- Tested with CartPole_PPO and CarPole_DQN
- Normalizing filters don't work right now (see #49) and are disabled in CartPole_PPO preset
- Checkpointing is disabled for MXNet
This commit is contained in:
Sina Afrooze
2018-11-07 07:07:15 -08:00
committed by Itai Caspi
parent e7a91b4dc3
commit 5fadb9c18e
39 changed files with 3864 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
rl_coach/presets/CartPole_PPO.py
View File

@@ -49,8 +49,8 @@ agent_params.algorithm.distributed_coach_synchronization_type = DistributedCoach
agent_params.exploration = EGreedyParameters()
agent_params.exploration.epsilon_schedule = LinearSchedule(1.0, 0.01, 10000)
agent_params.pre_network_filter.add_observation_filter('observation', 'normalize_observation',
ObservationNormalizationFilter(name='normalize_observation'))
# agent_params.pre_network_filter.add_observation_filter('observation', 'normalize_observation',
# ObservationNormalizationFilter(name='normalize_observation'))
###############
# Environment #