preventing the evaluation agent from getting stuck in bad policies by updating from the global network during episodes

2025-12-17 19:20:19 +01:00 · 2017-10-25 10:28:45 +03:00
parent d3c6860421
commit 39cf78074c
2 changed files with 6 additions and 0 deletions
--- a/configurations.py
+++ b/configurations.py
@@ -72,6 +72,7 @@ class AgentParameters:
    # Agent parameters
    num_consecutive_playing_steps = 1
    num_consecutive_training_steps = 1
+    update_evaluation_agent_network_after_every_num_steps = 3000
    bootstrap_total_return_from_old_policy = False
    n_step = -1
    num_episodes_in_experience_replay = 200