diff --git a/crates/ml/src/trainers/dqn/config.rs b/crates/ml/src/trainers/dqn/config.rs index 633325fa3..4791e8b0c 100644 --- a/crates/ml/src/trainers/dqn/config.rs +++ b/crates/ml/src/trainers/dqn/config.rs @@ -1656,7 +1656,7 @@ impl DQNHyperparameters { exposure_aux_weight: 0.5, exposure_aux_warmup_epochs: 5, // v8: Dense micro-reward, TD(λ), PopArt, curriculum, hindsight - micro_reward_scale: 0.001, + micro_reward_scale: 0.01, td_lambda: 0.9, max_trace_length: 7, popart_enabled: false, // disabled by default until wired