Apply suggestions from code review.
This commit is contained in:
@@ -1,11 +1,17 @@
|
||||
training_config:
|
||||
rl_framework: RLLIB_multi_agent
|
||||
# rl_framework: SB3
|
||||
rl_algorithm: PPO
|
||||
seed: 333
|
||||
n_learn_episodes: 1
|
||||
n_eval_episodes: 5
|
||||
max_steps_per_episode: 256
|
||||
deterministic_eval: false
|
||||
n_agents: 2
|
||||
agent_references:
|
||||
- defender_1
|
||||
- defender_2
|
||||
|
||||
|
||||
io_settings:
|
||||
save_checkpoints: true
|
||||
checkpoint_interval: 5
|
||||
|
||||
Reference in New Issue
Block a user