Upload ThreeSixNine checkpoint envstep_45000.pth.tar

README.md

@@ -0,0 +1,22 @@
+---
+library_name: pytorch
+tags:
+- efficientzero
+- muzero
+- board-game
+- combinatorial-reasoning
+- crpt
+---
+
+# ThreeSixNine-CK
+
+Latest exported EfficientZero checkpoint for `three_six_nine` from the simplified-five CRPT training runs.
+
+- Checkpoint: `checkpoints/envstep_45000.pth.tar`
+- Source path: `/workspace/combinatorial_reasoning_post_training/models/three_six_nine_dual_eval_continuation_20260519/round-01/three_six_nine/attempt-01_260519_131901/ckpt/envstep_45000.pth.tar`
+- Source attempt directory: `/workspace/combinatorial_reasoning_post_training/models/three_six_nine_dual_eval_continuation_20260519/round-01/three_six_nine/attempt-01_260519_131901`
+- W&B project: `crpt-three-six-nine-dual-eval-continuation`
+- W&B run: `dual_eval_20260519__three_six_nine__a01`
+- Uploaded at: `2026-05-19T15:04:12Z`
+
+Companion metadata is stored under `metadata/`, including the resolved LightZero config when available.

checkpoints/envstep_45000.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80846b7a0cae29218e2be5e2bc158066daf43c2a733610dc76991e9bdc2a50f8
+size 202265995

metadata/total_config.py

@@ -0,0 +1,246 @@
+exp_config = {
+    'env': {
+        'manager': {
+            'episode_num': float("inf"),
+            'max_retry': 1,
+            'step_timeout': None,
+            'auto_reset': True,
+            'reset_timeout': None,
+            'retry_type': 'reset',
+            'retry_waiting_time': 0.1,
+            'shared_memory': False,
+            'copy_on_get': True,
+            'context': 'fork',
+            'wait_num': float("inf"),
+            'step_wait_timeout': None,
+            'connect_timeout': 60,
+            'reset_inplace': False,
+            'cfg_type': 'SyncSubprocessEnvManagerDict',
+            'type': 'subprocess'
+        },
+        'stop_value': 10000000000,
+        'n_evaluator_episode': 10,
+        'env_id': 'three_six_nine',
+        'battle_mode': 'self_play_mode',
+        'battle_mode_in_simulation_env': 'self_play_mode',
+        'bot_action_type': 'rule',
+        'agent_vs_human': False,
+        'prob_random_agent': 0,
+        'prob_expert_agent': 0,
+        'prob_random_action_in_bot': 0.0,
+        'channel_last': False,
+        'scale': True,
+        'render_mode': None,
+        'replay_path': None,
+        'alphazero_mcts_ctree': False,
+        'random_start_on_reset': False,
+        'random_start_min_moves': 0,
+        'random_start_max_moves': 0,
+        'random_start_even_ply': True,
+        'random_start_seed_offset': 0,
+        'cfg_type': 'ThreeSixNineEnvDict',
+        'type': 'three_six_nine',
+        'import_names':
+        ['custom_games.three_six_nine.envs.three_six_nine_env'],
+        'collector_env_num': 4,
+        'evaluator_env_num': 10,
+        'eval_random_start_enabled': True,
+        'eval_random_start_min_moves': 0,
+        'eval_random_start_max_moves': 20,
+        'eval_random_start_even_ply': True
+    },
+    'policy': {
+        'model': {
+            'model_type': 'conv',
+            'continuous_action_space': False,
+            'observation_shape': (3, 9, 9),
+            'self_supervised_learning_loss': True,
+            'categorical_distribution': True,
+            'image_channel': 3,
+            'frame_stack_num': 1,
+            'num_res_blocks': 1,
+            'num_channels': 64,
+            'reward_support_range': (-300.0, 301.0, 1.0),
+            'value_support_range': (-300.0, 301.0, 1.0),
+            'bias': True,
+            'discrete_action_encoding_type': 'one_hot',
+            'res_connection_in_dynamics': True,
+            'norm_type': 'BN',
+            'analysis_sim_norm': False,
+            'analysis_dormant_ratio': False,
+            'harmony_balance': False,
+            'lstm_hidden_size': 512,
+            'action_space_size': 81
+        },
+        'learn': {
+            'learner': {
+                'train_iterations': 1000000000,
+                'dataloader': {
+                    'num_workers': 0
+                },
+                'log_policy': True,
+                'hook': {
+                    'load_ckpt_before_run': '',
+                    'log_show_after_iter': 100,
+                    'save_ckpt_after_iter': 10000,
+                    'save_ckpt_after_run': True
+                },
+                'cfg_type': 'BaseLearnerDict'
+            },
+            'resume_training': False
+        },
+        'collect': {
+            'collector': {
+                'deepcopy_obs': False,
+                'transform_obs': False,
+                'collect_print_freq': 100,
+                'cfg_type': 'SampleSerialCollectorDict',
+                'type': 'sample'
+            }
+        },
+        'eval': {
+            'evaluator': {
+                'eval_freq': 1000,
+                'render': {
+                    'render_freq': -1,
+                    'mode': 'train_iter'
+                },
+                'figure_path': None,
+                'cfg_type': 'InteractionSerialEvaluatorDict',
+                'stop_value': 10000000000,
+                'n_episode': 10
+            }
+        },
+        'other': {
+            'replay_buffer': {
+                'type': 'advanced',
+                'replay_buffer_size': 4096,
+                'max_use': float("inf"),
+                'max_staleness': float("inf"),
+                'alpha': 0.6,
+                'beta': 0.4,
+                'anneal_step': 100000,
+                'enable_track_used_data': False,
+                'deepcopy': False,
+                'thruput_controller': {
+                    'push_sample_rate_limit': {
+                        'max': float("inf"),
+                        'min': 0
+                    },
+                    'window_seconds': 30,
+                    'sample_min_limit_ratio': 1
+                },
+                'monitor': {
+                    'sampled_data_attr': {
+                        'average_range': 5,
+                        'print_freq': 200
+                    },
+                    'periodic_thruput': {
+                        'seconds': 60
+                    }
+                },
+                'cfg_type': 'AdvancedReplayBufferDict'
+            },
+            'commander': {
+                'cfg_type': 'BaseSerialCommanderDict'
+            }
+        },
+        'on_policy': False,
+        'cuda': True,
+        'multi_gpu': False,
+        'bp_update_sync': True,
+        'traj_len_inf': False,
+        'use_wandb': True,
+        'use_rnd_model': False,
+        'sampled_algo': False,
+        'gumbel_algo': False,
+        'mcts_ctree': True,
+        'collector_env_num': 4,
+        'evaluator_env_num': 10,
+        'env_type': 'board_games',
+        'action_type': 'varied_action_space',
+        'battle_mode': 'self_play_mode',
+        'monitor_extra_statistics': True,
+        'game_segment_length': 81,
+        'eval_offline': False,
+        'calculate_dormant_ratio': False,
+        'analysis_sim_norm': False,
+        'analysis_dormant_ratio': False,
+        'transform2string': False,
+        'gray_scale': False,
+        'use_augmentation': False,
+        'augmentation': ['shift', 'intensity'],
+        'ignore_done': False,
+        'update_per_collect': 10,
+        'replay_ratio': 0.25,
+        'batch_size': 128,
+        'optim_type': 'Adam',
+        'learning_rate': 0.003,
+        'target_update_freq': 100,
+        'target_update_freq_for_intrinsic_reward': 1000,
+        'weight_decay': 0.0001,
+        'momentum': 0.9,
+        'grad_clip_value': 0.5,
+        'n_episode': 4,
+        'num_segments': 8,
+        'num_simulations': 20,
+        'discount_factor': 1,
+        'td_steps': 81,
+        'num_unroll_steps': 5,
+        'reward_loss_weight': 1,
+        'value_loss_weight': 0.25,
+        'policy_loss_weight': 1,
+        'policy_entropy_weight': 0,
+        'ssl_loss_weight': 2,
+        'piecewise_decay_lr_scheduler': False,
+        'threshold_training_steps_for_final_lr': 50000,
+        'manual_temperature_decay': False,
+        'threshold_training_steps_for_final_temperature': 100000,
+        'fixed_temperature_value': 0.25,
+        'use_ture_chance_label_in_chance_encoder': False,
+        'reanalyze_noise': True,
+        'reuse_search': False,
+        'collect_with_pure_policy': False,
+        'use_priority': False,
+        'priority_prob_alpha': 0.6,
+        'priority_prob_beta': 0.4,
+        'root_dirichlet_alpha': 0.3,
+        'root_noise_weight': 0.25,
+        'random_collect_episode_num': 0,
+        'eps': {
+            'eps_greedy_exploration_in_collect': False,
+            'type': 'linear',
+            'start': 1.0,
+            'end': 0.05,
+            'decay': 100000
+        },
+        'cfg_type': 'EfficientZeroPolicyDict',
+        'lstm_horizon_len': 5,
+        'type': 'efficientzero',
+        'import_names': ['lzero.policy.efficientzero'],
+        'model_path':
+        '/workspace/combinatorial_reasoning_post_training/models/simplified5_constant_lr_fixed_20260519/round-01/three_six_nine/attempt-01_260519_093513/ckpt/envstep_90000.pth.tar',
+        'reanalyze_ratio': 0.0,
+        'eval_freq': 100001,
+        'replay_buffer_size': 50000,
+        'best_ckpt_strategy': 'raw',
+        'best_ckpt_ema_alpha': 0.3,
+        'best_ckpt_min_episodes': 20,
+        'battle_mode_in_simulation_env': 'self_play_mode',
+        'eval_opponent_type': 'env_bot_and_previous_best_checkpoint',
+        'previous_best_checkpoint': {
+            'path': None,
+            'selector': 'best',
+            'update_policy': 'on_new_best',
+            'num_simulations': 10,
+            'n_evaluator_episode': 10,
+            'evaluator_env_num': 10,
+            'promotion_threshold': 0.0,
+            'fallback_to_env_bot': False
+        },
+        'device': 'cuda'
+    },
+    'exp_name':
+    'models/three_six_nine_dual_eval_continuation_20260519/round-01/three_six_nine/attempt-01_260519_131901',
+    'seed': 0
+}

metadata/upload_manifest.json

@@ -0,0 +1,15 @@
+{
+  "checkpoint_mtime_utc": "2026-05-19T15:03:41Z",
+  "checkpoint_size_bytes": 202265995,
+  "display_name": "ThreeSixNine",
+  "game_id": "three_six_nine",
+  "path_in_repo": "checkpoints/envstep_45000.pth.tar",
+  "repo_id": "LorMolf/ThreeSixNine-CK",
+  "source_attempt_dir": "/workspace/combinatorial_reasoning_post_training/models/three_six_nine_dual_eval_continuation_20260519/round-01/three_six_nine/attempt-01_260519_131901",
+  "source_checkpoint": "/workspace/combinatorial_reasoning_post_training/models/three_six_nine_dual_eval_continuation_20260519/round-01/three_six_nine/attempt-01_260519_131901/ckpt/envstep_45000.pth.tar",
+  "source_checkpoint_index": "/workspace/combinatorial_reasoning_post_training/models/three_six_nine_dual_eval_continuation_20260519/round-01/three_six_nine/attempt-01_260519_131901/ckpt/checkpoint_index.yaml",
+  "source_total_config": "/workspace/combinatorial_reasoning_post_training/models/three_six_nine_dual_eval_continuation_20260519/round-01/three_six_nine/attempt-01_260519_131901/total_config.py",
+  "uploaded_at_utc": "2026-05-19T15:04:12Z",
+  "wandb_project": "crpt-three-six-nine-dual-eval-continuation",
+  "wandb_run": "dual_eval_20260519__three_six_nine__a01"
+}