majiang

Public

• NotificationsYou must be signed in to change notification settings
• Fork0 (0)
• Star0 (0)You must be signed in to star a repository

About

No description, website, or topics provided.

Activity

Stars

0 stars

Watchers

0 watching

Forks

0 forks

Report repository

main

BranchesTags

Go to file

Code

Open more actions menu

Latest commit

 

History

24 Commits

24 Commits

Folders and files

Name		Name	Last commit message	Last commit date
Action_Value_20260729_v1		Action_Value_20260729_v1
Aligned_V1V2_20260714		Aligned_V1V2_20260714
Candidate_oracle_augmented_smoke		Candidate_oracle_augmented_smoke
Candidate_oracle_rule_mask_smoke		Candidate_oracle_rule_mask_smoke
Candidate_oracle_smoke		Candidate_oracle_smoke
Candidate_oracle_smoke_resampled		Candidate_oracle_smoke_resampled
Candidate_oracle_v1_go_nogo		Candidate_oracle_v1_go_nogo
Candidate_oracle_v1_greedy_smoke		Candidate_oracle_v1_greedy_smoke
Candidate_oracle_v1_pilot		Candidate_oracle_v1_pilot
Candidate_oracle_v1_pilot_heldout		Candidate_oracle_v1_pilot_heldout
Candidate_oracle_v1_scaleup_train		Candidate_oracle_v1_scaleup_train
Candidate_oracle_v1_scaleup_valid		Candidate_oracle_v1_scaleup_valid
Continuous_Gate_E2_ladder_3seed_200games		Continuous_Gate_E2_ladder_3seed_200games
E3_GateValue_20260806_v1		E3_GateValue_20260806_v1
E3_GateValue_20260806_v2		E3_GateValue_20260806_v2
GRPO_pilot_game_eval		GRPO_pilot_game_eval
Gate1_aligned_smoke_20games		Gate1_aligned_smoke_20games
Gate1_shanten_fixed_smoke_50games		Gate1_shanten_fixed_smoke_50games
Gate_Value_20260730_v1		Gate_Value_20260730_v1
Gate_Value_20260730_v2		Gate_Value_20260730_v2
Gate_Value_Belief_20260807_v3		Gate_Value_Belief_20260807_v3
H2_Full_Learned_20260716_h2_full_learned		H2_Full_Learned_20260716_h2_full_learned
H2_Gate_Route_20260715_h2_gate_v1clean		H2_Gate_Route_20260715_h2_gate_v1clean
H2_Gate_Route_20260715_h2_gate_v1clean_smoke/gate_oracle		H2_Gate_Route_20260715_h2_gate_v1clean_smoke/gate_oracle
H2_NeuralGateV2_2seed_200games_gpu1_now		H2_NeuralGateV2_2seed_200games_gpu1_now
H2_Neural_Fast_3seed_200games		H2_Neural_Fast_3seed_200games
H2_Neural_ValueGate_5seed_500games		H2_Neural_ValueGate_5seed_500games
H2_ValueGate_SFTonly_smoke_1seed_100games		H2_ValueGate_SFTonly_smoke_1seed_100games
H2_Value_Gate_20260716		H2_Value_Gate_20260716
H2_aligned_v32_4variants_10seed_1000games		H2_aligned_v32_4variants_10seed_1000games
H2_common_auto_hu_50260627_4variants_10seed_1000games		H2_common_auto_hu_50260627_4variants_10seed_1000games
H2_common_hu_L0_L1_L2v2_10seed_1000games_gpu0_6parallel		H2_common_hu_L0_L1_L2v2_10seed_1000games_gpu0_6parallel
H2_common_hu_L0_L1_L2v2_2seed_200games_6parallel		H2_common_hu_L0_L1_L2v2_2seed_200games_6parallel
H2_gate_learned_relaxed_smoke		H2_gate_learned_relaxed_smoke
H2_neural_gate_margin_sweep_2seed_500games		H2_neural_gate_margin_sweep_2seed_500games
H2_no_auto_hu_2seed_200games		H2_no_auto_hu_2seed_200games
H2_no_auto_hu_50260627_4variants_10seed_1000games		H2_no_auto_hu_50260627_4variants_10seed_1000games
MASK_Full_20260716		MASK_Full_20260716
Neural_FFR_proxy_smoke		Neural_FFR_proxy_smoke
Neural_Gate_20260723_v1		Neural_Gate_20260723_v1
Neural_Gate_20260723_v2		Neural_Gate_20260723_v2
Neural_Gate_20260723_v3		Neural_Gate_20260723_v3
Neural_Gate_20260723_v31		Neural_Gate_20260723_v31
Neural_Gate_20260724_v32_retry		Neural_Gate_20260724_v32_retry
Neural_Gate_20260724_v33		Neural_Gate_20260724_v33
Neural_Gate_20260724_v34		Neural_Gate_20260724_v34
Neural_Gate_20260725_v32_aligned		Neural_Gate_20260725_v32_aligned
Neural_Gate_20260729_v3_dagger		Neural_Gate_20260729_v3_dagger
Neural_LLM_L0_L1_L2continuous_3seed_200games		Neural_LLM_L0_L1_L2continuous_3seed_200games
Neural_LLM_L0_L1_L2continuous_5seed_500games		Neural_LLM_L0_L1_L2continuous_5seed_500games
Neural_LLM_L0_L1_L2continuous_newseeds2_5seed_1000games		Neural_LLM_L0_L1_L2continuous_newseeds2_5seed_1000games
Neural_LLM_L0_L1_L2continuous_newseeds_5seed_1000games		Neural_LLM_L0_L1_L2continuous_newseeds_5seed_1000games
Neural_LLM_L0_L1_L2continuous_newseeds_5seed_500games		Neural_LLM_L0_L1_L2continuous_newseeds_5seed_500games
Neural_LLM_L0_L1_L2continuous_v1v2_10seed_1000games		Neural_LLM_L0_L1_L2continuous_v1v2_10seed_1000games
Neural_LLM_L2_continuous_v2_40260627_5seed_1000games		Neural_LLM_L2_continuous_v2_40260627_5seed_1000games
Neural_LLM_L2_continuous_v3_50260627_10seed_1000games		Neural_LLM_L2_continuous_v3_50260627_10seed_1000games
Neural_LLM_L2_continuous_v4_50260627_10seed_1000games		Neural_LLM_L2_continuous_v4_50260627_10seed_1000games
Neural_LLM_L2_continuous_v5_50260627_10seed_1000games		Neural_LLM_L2_continuous_v5_50260627_10seed_1000games
Neural_LLM_L2_continuous_v6_60260627_10seed_1000games		Neural_LLM_L2_continuous_v6_60260627_10seed_1000games
Neural_LLM_L2continuous_valuegatefix_5seed_500games		Neural_LLM_L2continuous_valuegatefix_5seed_500games
Neural_opponent_data		Neural_opponent_data
Neural_opponent_model		Neural_opponent_model
Neural_opponent_model_smoke		Neural_opponent_model_smoke
Neural_opponent_selfplay_100games		Neural_opponent_selfplay_100games
Neural_opponent_smoke_eval		Neural_opponent_smoke_eval
Reranker_aligned_20260715		Reranker_aligned_20260715
Reranker_env_reward_eval_action_only_v3_heldout		Reranker_env_reward_eval_action_only_v3_heldout
Reranker_env_reward_eval_action_only_v3_scoring_heldout		Reranker_env_reward_eval_action_only_v3_scoring_heldout
Reranker_env_reward_eval_action_only_v3_train		Reranker_env_reward_eval_action_only_v3_train
Reranker_env_reward_eval_multimode_v2_heldout		Reranker_env_reward_eval_multimode_v2_heldout
Reranker_env_reward_eval_multimode_v2_range20_heldout		Reranker_env_reward_eval_multimode_v2_range20_heldout
Reranker_env_reward_eval_v4_canonical_base		Reranker_env_reward_eval_v4_canonical_base
Reranker_env_reward_eval_v4_no_reference_heldout		Reranker_env_reward_eval_v4_no_reference_heldout
Reranker_env_reward_eval_v4_no_reference_pretrain		Reranker_env_reward_eval_v4_no_reference_pretrain
Reranker_grpo_data		Reranker_grpo_data
Reranker_grpo_oracle_multimode_v2		Reranker_grpo_oracle_multimode_v2
Reranker_sft_data		Reranker_sft_data
Reranker_sft_eval_heldout		Reranker_sft_eval_heldout
Reranker_teacher_l2_public_3seeds_100games		Reranker_teacher_l2_public_3seeds_100games
Reranker_teacher_safe_deceive_public_1seed_100games		Reranker_teacher_safe_deceive_public_1seed_100games
Reranker_teacher_safe_smoke		Reranker_teacher_safe_smoke
Reranker_teacher_smoke		Reranker_teacher_smoke
Reranker_validation_public_1seed_20games		Reranker_validation_public_1seed_20games
Shared_Base_20260727_v1		Shared_Base_20260727_v1
Shared_Base_20260728_v2		Shared_Base_20260728_v2
Shared_Base_20260728_v3		Shared_Base_20260728_v3
Shared_Base_v2_action_audit_smoke		Shared_Base_v2_action_audit_smoke
Shared_Base_v2_completion_smoke		Shared_Base_v2_completion_smoke
Shared_Base_v2_grpo_hu_smoke		Shared_Base_v2_grpo_hu_smoke
Shared_Base_v2_metrics_smoke		Shared_Base_v2_metrics_smoke
V1_Clean_20260715_v1_clean		V1_Clean_20260715_v1_clean
V1_L0L1L2_5seeds_500games		V1_L0L1L2_5seeds_500games
V1_L0L1L2_reranker_3seeds_200games		V1_L0L1L2_reranker_3seeds_200games
V1_aligned_ladder_pilot_1seed_50games		V1_aligned_ladder_pilot_1seed_50games
V1_calibrated_blend_ladder_pilot_1seed_50games		V1_calibrated_blend_ladder_pilot_1seed_50games
V1_inherited_l1_l2_pilot_1seed_50games		V1_inherited_l1_l2_pilot_1seed_50games
V1_public_reranker_smoke		V1_public_reranker_smoke
V1_shanten_fixed_ladder_pilot_1seed_50games		V1_shanten_fixed_ladder_pilot_1seed_50games
V1_shared_backbone_ladder_pilot_1seed_50games		V1_shared_backbone_ladder_pilot_1seed_50games
V1_ukeire_guard_l1_l2_pilot_1seed_50games		V1_ukeire_guard_l1_l2_pilot_1seed_50games
View all files

About

No description, website, or topics provided.

Activity

Stars

0 stars

Watchers

0 watching

Forks

0 forks

Report repository

Releases

Packages

Contributors

Languages