From 6afec90484bbf47dee05fdf525e26a3ebe028e9b Mon Sep 17 00:00:00 2001 From: Ilya Zisman Date: Tue, 1 Aug 2023 23:57:35 +0300 Subject: [PATCH] Fix reward scale for DT configs (#75) --- configs/offline/dt/halfcheetah/medium_expert_v2.yaml | 2 +- configs/offline/dt/halfcheetah/medium_replay_v2.yaml | 2 +- configs/offline/dt/halfcheetah/medium_v2.yaml | 2 +- configs/offline/dt/hopper/medium_expert_v2.yaml | 2 +- configs/offline/dt/hopper/medium_replay_v2.yaml | 2 +- configs/offline/dt/hopper/medium_v2.yaml | 2 +- configs/offline/dt/walker2d/medium_expert_v2.yaml | 2 +- configs/offline/dt/walker2d/medium_replay_v2.yaml | 2 +- configs/offline/dt/walker2d/medium_v2.yaml | 2 +- 9 files changed, 9 insertions(+), 9 deletions(-) diff --git a/configs/offline/dt/halfcheetah/medium_expert_v2.yaml b/configs/offline/dt/halfcheetah/medium_expert_v2.yaml index 900ac056..16fffc1f 100644 --- a/configs/offline/dt/halfcheetah/medium_expert_v2.yaml +++ b/configs/offline/dt/halfcheetah/medium_expert_v2.yaml @@ -23,7 +23,7 @@ num_layers: 3 num_workers: 4 project: "CORL" residual_dropout: 0.1 -reward_scale: 1.0 +reward_scale: 0.001 seq_len: 20 target_returns: [12000.0, 6000.0] train_seed: 10 diff --git a/configs/offline/dt/halfcheetah/medium_replay_v2.yaml b/configs/offline/dt/halfcheetah/medium_replay_v2.yaml index e570322d..6f12d0f1 100644 --- a/configs/offline/dt/halfcheetah/medium_replay_v2.yaml +++ b/configs/offline/dt/halfcheetah/medium_replay_v2.yaml @@ -23,7 +23,7 @@ num_layers: 3 num_workers: 4 project: "CORL" residual_dropout: 0.1 -reward_scale: 1.0 +reward_scale: 0.001 seq_len: 20 target_returns: [12000.0, 6000.0] train_seed: 10 diff --git a/configs/offline/dt/halfcheetah/medium_v2.yaml b/configs/offline/dt/halfcheetah/medium_v2.yaml index c5d46e33..8b6e4417 100644 --- a/configs/offline/dt/halfcheetah/medium_v2.yaml +++ b/configs/offline/dt/halfcheetah/medium_v2.yaml @@ -23,7 +23,7 @@ num_layers: 3 num_workers: 4 project: "CORL" residual_dropout: 0.1 -reward_scale: 1.0 +reward_scale: 0.001 seq_len: 20 target_returns: [12000.0, 6000.0] train_seed: 10 diff --git a/configs/offline/dt/hopper/medium_expert_v2.yaml b/configs/offline/dt/hopper/medium_expert_v2.yaml index 18d9d07e..3a7b7d58 100644 --- a/configs/offline/dt/hopper/medium_expert_v2.yaml +++ b/configs/offline/dt/hopper/medium_expert_v2.yaml @@ -23,7 +23,7 @@ num_layers: 3 num_workers: 4 project: "CORL" residual_dropout: 0.1 -reward_scale: 1.0 +reward_scale: 0.001 seq_len: 20 target_returns: [3600.0, 1800.0] train_seed: 10 diff --git a/configs/offline/dt/hopper/medium_replay_v2.yaml b/configs/offline/dt/hopper/medium_replay_v2.yaml index b9311d1c..8f61412b 100644 --- a/configs/offline/dt/hopper/medium_replay_v2.yaml +++ b/configs/offline/dt/hopper/medium_replay_v2.yaml @@ -23,7 +23,7 @@ num_layers: 3 num_workers: 4 project: "CORL" residual_dropout: 0.1 -reward_scale: 1.0 +reward_scale: 0.001 seq_len: 20 target_returns: [3600.0, 1800.0] train_seed: 10 diff --git a/configs/offline/dt/hopper/medium_v2.yaml b/configs/offline/dt/hopper/medium_v2.yaml index 7e8fa9f3..58c532dc 100644 --- a/configs/offline/dt/hopper/medium_v2.yaml +++ b/configs/offline/dt/hopper/medium_v2.yaml @@ -23,7 +23,7 @@ num_layers: 3 num_workers: 4 project: "CORL" residual_dropout: 0.1 -reward_scale: 1.0 +reward_scale: 0.001 seq_len: 20 target_returns: [3600.0, 1800.0] train_seed: 10 diff --git a/configs/offline/dt/walker2d/medium_expert_v2.yaml b/configs/offline/dt/walker2d/medium_expert_v2.yaml index 32e1e38b..2ac29a9d 100644 --- a/configs/offline/dt/walker2d/medium_expert_v2.yaml +++ b/configs/offline/dt/walker2d/medium_expert_v2.yaml @@ -23,7 +23,7 @@ num_layers: 3 num_workers: 4 project: "CORL" residual_dropout: 0.1 -reward_scale: 1.0 +reward_scale: 0.001 seq_len: 20 target_returns: [5000.0, 2500.0] train_seed: 10 diff --git a/configs/offline/dt/walker2d/medium_replay_v2.yaml b/configs/offline/dt/walker2d/medium_replay_v2.yaml index a703f403..daa394da 100644 --- a/configs/offline/dt/walker2d/medium_replay_v2.yaml +++ b/configs/offline/dt/walker2d/medium_replay_v2.yaml @@ -23,7 +23,7 @@ num_layers: 3 num_workers: 4 project: "CORL" residual_dropout: 0.1 -reward_scale: 1.0 +reward_scale: 0.001 seq_len: 20 target_returns: [5000.0, 2500.0] train_seed: 10 diff --git a/configs/offline/dt/walker2d/medium_v2.yaml b/configs/offline/dt/walker2d/medium_v2.yaml index a06b064e..630b8685 100644 --- a/configs/offline/dt/walker2d/medium_v2.yaml +++ b/configs/offline/dt/walker2d/medium_v2.yaml @@ -23,7 +23,7 @@ num_layers: 3 num_workers: 4 project: "CORL" residual_dropout: 0.1 -reward_scale: 1.0 +reward_scale: 0.001 seq_len: 20 target_returns: [5000.0, 2500.0] train_seed: 10