Loading scripts/debug/debug_api_frozenlake/env_config.yaml +1 −1 Original line number Original line Diff line number Diff line Loading @@ -3,6 +3,6 @@ env1: env_config: env_config: render_mode: vision render_mode: vision prompt_format: free_think prompt_format: free_think use_accuracy_reward: false use_state_reward: false train_size: 0 train_size: 0 test_size: 2 test_size: 2 No newline at end of file scripts/exps/finegrained/frozenlake/free_think/env_config.yaml +1 −1 Original line number Original line Diff line number Diff line Loading @@ -3,6 +3,6 @@ env1: env_config: env_config: render_mode: vision render_mode: vision prompt_format: free_think prompt_format: free_think use_accuracy_reward: false use_state_reward: false train_size: 10000 train_size: 10000 test_size: 128 test_size: 128 No newline at end of file scripts/exps/finegrained/frozenlake/grounding/env_config.yaml +1 −1 Original line number Original line Diff line number Diff line Loading @@ -3,6 +3,6 @@ env1: env_config: env_config: render_mode: vision render_mode: vision prompt_format: grounding prompt_format: grounding use_accuracy_reward: false use_state_reward: false train_size: 10000 train_size: 10000 test_size: 128 test_size: 128 No newline at end of file scripts/exps/finegrained/frozenlake/grounding_worldmodeling/env_config.yaml +1 −1 Original line number Original line Diff line number Diff line Loading @@ -3,6 +3,6 @@ env1: env_config: env_config: render_mode: vision render_mode: vision prompt_format: grounding_worldmodeling prompt_format: grounding_worldmodeling use_accuracy_reward: false use_state_reward: false train_size: 10000 train_size: 10000 test_size: 128 test_size: 128 No newline at end of file scripts/exps/finegrained/frozenlake/no_think/env_config.yaml +1 −1 Original line number Original line Diff line number Diff line Loading @@ -3,6 +3,6 @@ env1: env_config: env_config: render_mode: vision render_mode: vision prompt_format: no_think prompt_format: no_think use_accuracy_reward: false use_state_reward: false train_size: 10000 train_size: 10000 test_size: 128 test_size: 128 No newline at end of file Loading
scripts/debug/debug_api_frozenlake/env_config.yaml +1 −1 Original line number Original line Diff line number Diff line Loading @@ -3,6 +3,6 @@ env1: env_config: env_config: render_mode: vision render_mode: vision prompt_format: free_think prompt_format: free_think use_accuracy_reward: false use_state_reward: false train_size: 0 train_size: 0 test_size: 2 test_size: 2 No newline at end of file
scripts/exps/finegrained/frozenlake/free_think/env_config.yaml +1 −1 Original line number Original line Diff line number Diff line Loading @@ -3,6 +3,6 @@ env1: env_config: env_config: render_mode: vision render_mode: vision prompt_format: free_think prompt_format: free_think use_accuracy_reward: false use_state_reward: false train_size: 10000 train_size: 10000 test_size: 128 test_size: 128 No newline at end of file
scripts/exps/finegrained/frozenlake/grounding/env_config.yaml +1 −1 Original line number Original line Diff line number Diff line Loading @@ -3,6 +3,6 @@ env1: env_config: env_config: render_mode: vision render_mode: vision prompt_format: grounding prompt_format: grounding use_accuracy_reward: false use_state_reward: false train_size: 10000 train_size: 10000 test_size: 128 test_size: 128 No newline at end of file
scripts/exps/finegrained/frozenlake/grounding_worldmodeling/env_config.yaml +1 −1 Original line number Original line Diff line number Diff line Loading @@ -3,6 +3,6 @@ env1: env_config: env_config: render_mode: vision render_mode: vision prompt_format: grounding_worldmodeling prompt_format: grounding_worldmodeling use_accuracy_reward: false use_state_reward: false train_size: 10000 train_size: 10000 test_size: 128 test_size: 128 No newline at end of file
scripts/exps/finegrained/frozenlake/no_think/env_config.yaml +1 −1 Original line number Original line Diff line number Diff line Loading @@ -3,6 +3,6 @@ env1: env_config: env_config: render_mode: vision render_mode: vision prompt_format: no_think prompt_format: no_think use_accuracy_reward: false use_state_reward: false train_size: 10000 train_size: 10000 test_size: 128 test_size: 128 No newline at end of file
