episode_id int64 0 511 | env_id stringclasses 2
values | model_name stringclasses 1
value | opponent_name stringclasses 1
value | completion_status stringclasses 2
values | model_outcome stringclasses 2
values | model_reward float64 -1 1 | opponent_reward float64 -1 1 | num_turns int64 2 20 | duration float64 2.78 134 | trajectory listlengths 25 61 | observations listlengths 25 61 | formatted_observations listlengths 25 61 | reasoning listlengths 25 61 | actions listlengths 25 61 | player_ids listlengths 25 61 | model_names listlengths 25 61 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
13 | TicTacToe-v0 | qwen/Qwen3-4B-Base | openai/gpt-4.1-mini | complete | win | 1 | -1 | 8 | 47.602582 | [{"action":"[4]","env_id":"TicTacToe-v0","episode_id":13,"final_reward":0.0,"formatted_observation":(...TRUNCATED) | ["You are Player 0 in Tic Tac Toe.\nYour goal is to win three in a row (horizontally, vertically, or(...TRUNCATED) | ["","","<|im_start|>user\nYou are playing a two-player zero-sum game. Make valid actions to win.\nOb(...TRUNCATED) | ["","","You are playing a two-player zero-sum game. Make valid actions to win.\nObservation: 2-Playe(...TRUNCATED) | ["[4]","[bet]","","","","","[Bid: 3, 6]","[2 5]","","","","Hello! I have 10 Wood (value 15 each) and(...TRUNCATED) | [
0,
1,
0,
0,
0,
0,
0,
0,
1,
0,
0,
1,
0,
0,
1,
1,
1,
0,
0,
1,
1,
0,
1,
0,
1,
1,
0,
1,
1,
1,
1,
0,
0,
0,
0,
0,
0,
1,
1,
1,
0,
1
] | ["openai/gpt-4.1-mini","openai/gpt-4.1-mini","qwen/Qwen3-4B-Base","qwen/Qwen3-4B-Base","qwen/Qwen3-4(...TRUNCATED) |
504 | TicTacToe-v0 | qwen/Qwen3-4B-Base | openai/gpt-4.1-mini | invalid | loss | -1 | 0 | 5 | 38.702471 | [{"action":"[4]","env_id":"TicTacToe-v0","episode_id":504,"final_reward":1.0,"formatted_observation"(...TRUNCATED) | ["You are Player 0 in Tic Tac Toe.\nYour goal is to win three in a row (horizontally, vertically, or(...TRUNCATED) | ["<|im_start|>user\nYou are playing a two-player zero-sum game. Make valid actions to win.\nObservat(...TRUNCATED) | ["Assistant: To make a strategic move in Tic Tac Toe as Player 0 ('O'), we need to consider the foll(...TRUNCATED) | ["[4]","[bet]","[right]","","[col 3]","","[Bid: 1, 3]","","[0]","[call]","","Hello! I see you have r(...TRUNCATED) | [
0,
1,
0,
0,
0,
0,
0,
0,
1,
0,
1,
1,
1,
0,
1,
0,
0,
0,
1,
0,
1,
1,
1,
1,
0,
1,
1,
0,
0,
0,
0,
1,
0,
1,
1,
0,
1
] | ["qwen/Qwen3-4B-Base","openai/gpt-4.1-mini","openai/gpt-4.1-mini","qwen/Qwen3-4B-Base","openai/gpt-4(...TRUNCATED) |
8 | TicTacToe-v0 | qwen/Qwen3-4B-Base | openai/gpt-4.1-mini | complete | loss | -1 | 1 | 7 | 36.066386 | [{"action":"[4]","env_id":"TicTacToe-v0","episode_id":8,"final_reward":0.0,"formatted_observation":"(...TRUNCATED) | ["You are Player 0 in Tic Tac Toe.\nYour goal is to win three in a row (horizontally, vertically, or(...TRUNCATED) | ["","","<|im_start|>user\nYou are playing a two-player zero-sum game. Make valid actions to win.\nOb(...TRUNCATED) | ["","","You are playing a two-player zero-sum game. Make valid actions to win.\nObservation: 2-Playe(...TRUNCATED) | ["[4]","[bet]","[up]","Hello! I'm interested in trading to improve our resource values. I have 10 Wo(...TRUNCATED) | [
0,
1,
0,
0,
0,
0,
0,
0,
1,
0,
1,
1,
1,
1,
0,
1,
1,
0,
0,
0,
0,
1,
1,
0,
1,
0,
0,
0,
1,
0,
1,
1,
1,
1,
0,
0,
1,
0,
0,
1,
0,
1,
1,
0,
1
] | ["openai/gpt-4.1-mini","openai/gpt-4.1-mini","qwen/Qwen3-4B-Base","openai/gpt-4.1-mini","qwen/Qwen3-(...TRUNCATED) |
43 | TicTacToe-v0 | qwen/Qwen3-4B-Base | openai/gpt-4.1-mini | invalid | loss | -1 | 0 | 6 | 42.684503 | [{"action":"[4]","env_id":"TicTacToe-v0","episode_id":43,"final_reward":0.0,"formatted_observation":(...TRUNCATED) | ["You are Player 0 in Tic Tac Toe.\nYour goal is to win three in a row (horizontally, vertically, or(...TRUNCATED) | ["","","","<|im_start|>user\nYou are playing a two-player zero-sum game. Make valid actions to win.\(...TRUNCATED) | ["","","","You are playing a two-player zero-sum game. Make valid actions to win.\nObservation: 2-Pl(...TRUNCATED) | ["[4]","[check]","I see you have valuable gold but less wood. I am interested in acquiring some gold(...TRUNCATED) | [
0,
1,
0,
0,
0,
0,
0,
0,
1,
0,
1,
0,
0,
1,
1,
1,
1,
0,
0,
1,
1,
1,
1,
1,
0,
0,
0,
0,
1,
1,
1,
0,
1,
0,
1
] | ["openai/gpt-4.1-mini","openai/gpt-4.1-mini","openai/gpt-4.1-mini","qwen/Qwen3-4B-Base","qwen/Qwen3-(...TRUNCATED) |
507 | TicTacToe-v0 | qwen/Qwen3-4B-Base | openai/gpt-4.1-mini | invalid | loss | -1 | 0 | 8 | 54.08497 | [{"action":"[4]","env_id":"TicTacToe-v0","episode_id":507,"final_reward":0.0,"formatted_observation"(...TRUNCATED) | ["You are Player 0 in Tic Tac Toe.\nYour goal is to win three in a row (horizontally, vertically, or(...TRUNCATED) | ["","","<|im_start|>user\nYou are playing a two-player zero-sum game. Make valid actions to win.\nOb(...TRUNCATED) | ["","","You are playing a two-player zero-sum game. Make valid actions to win.\nObservation: \n[GAME(...TRUNCATED) | ["[4]","[bet]","","[d]","","[9]","[Bid: 2, 5]","[2 2]","4","","Hello! I see you have some resources.(...TRUNCATED) | [
0,
1,
0,
0,
0,
0,
0,
0,
1,
0,
1,
1,
0,
1,
1,
1,
1,
0,
0,
0,
0,
1,
0,
1,
1,
0,
1,
0,
1,
0,
1,
1,
0,
0,
1,
0,
0,
1
] | ["openai/gpt-4.1-mini","openai/gpt-4.1-mini","qwen/Qwen3-4B-Base","openai/gpt-4.1-mini","qwen/Qwen3-(...TRUNCATED) |
98 | TicTacToe-v0 | qwen/Qwen3-4B-Base | openai/gpt-4.1-mini | invalid | loss | -1 | 0 | 6 | 47.105632 | [{"action":"","env_id":"TicTacToe-v0","episode_id":98,"final_reward":-1.0,"formatted_observation":"<(...TRUNCATED) | ["You are Player 0 in Tic Tac Toe.\nYour goal is to win three in a row (horizontally, vertically, or(...TRUNCATED) | ["<|im_start|>user\nYou are playing a two-player zero-sum game. Make valid actions to win.\nObservat(...TRUNCATED) | ["You are playing a two-player zero-sum game. Make valid actions to win.\nObservation: You are Playe(...TRUNCATED) | ["","[bet]","[d]","","","","[Bid: 3, 5]","[0 1]","","[call]","","Hello! I have 10 Wood (value 15 eac(...TRUNCATED) | [
0,
1,
0,
0,
0,
0,
0,
0,
0,
0,
1,
1,
0,
0,
1,
1,
0,
1,
0,
0,
0,
1,
1,
0,
1,
1,
0,
0,
1,
0,
0,
1,
0,
1
] | ["qwen/Qwen3-4B-Base","qwen/Qwen3-4B-Base","openai/gpt-4.1-mini","qwen/Qwen3-4B-Base","qwen/Qwen3-4B(...TRUNCATED) |
129 | TicTacToe-v0 | qwen/Qwen3-4B-Base | openai/gpt-4.1-mini | invalid | loss | -1 | 0 | 3 | 27.061475 | [{"action":"[4]","env_id":"TicTacToe-v0","episode_id":129,"final_reward":0.0,"formatted_observation"(...TRUNCATED) | ["You are Player 0 in Tic Tac Toe.\nYour goal is to win three in a row (horizontally, vertically, or(...TRUNCATED) | ["","<|im_start|>user\nYou are playing a two-player zero-sum game. Make valid actions to win.\nObser(...TRUNCATED) | ["","You are playing a two-player zero-sum game. Make valid actions to win.\nObservation: \n[GAME] Y(...TRUNCATED) | ["[4]","","","I have 10 Wood (value 5 each) and 10 Gold (value 15 each). I'm looking to improve the (...TRUNCATED) | [
0,
1,
0,
0,
0,
0,
0,
0,
1,
1,
0,
1,
0,
1,
1,
1,
1,
1,
0,
0,
1,
1,
0,
1,
0,
1,
0,
0,
1,
0,
0,
1,
0,
1
] | ["openai/gpt-4.1-mini","qwen/Qwen3-4B-Base","qwen/Qwen3-4B-Base","openai/gpt-4.1-mini","qwen/Qwen3-4(...TRUNCATED) |
109 | TicTacToe-v0 | qwen/Qwen3-4B-Base | openai/gpt-4.1-mini | complete | win | 1 | -1 | 7 | 60.897818 | [{"action":"[4]","env_id":"TicTacToe-v0","episode_id":109,"final_reward":0.0,"formatted_observation"(...TRUNCATED) | ["You are Player 0 in Tic Tac Toe.\nYour goal is to win three in a row (horizontally, vertically, or(...TRUNCATED) | ["","","","<|im_start|>user\nYou are playing a two-player zero-sum game. Make valid actions to win.\(...TRUNCATED) | ["","","","You are playing a two-player zero-sum game. Make valid actions to win.\nObservation: 2-Pl(...TRUNCATED) | ["[4]","[bet]","Hello! I'm interested in improving my resource value. I have 10 Wood (value 5) and 1(...TRUNCATED) | [
0,
1,
0,
0,
0,
0,
0,
0,
1,
0,
1,
0,
1,
1,
1,
0,
1,
0,
0,
1,
1,
0,
1,
0,
1,
0,
0,
0,
1,
0,
1,
0,
1,
0,
1,
0,
1,
0,
0,
1,
1,
0,
0
] | ["openai/gpt-4.1-mini","openai/gpt-4.1-mini","openai/gpt-4.1-mini","qwen/Qwen3-4B-Base","openai/gpt-(...TRUNCATED) |
471 | TicTacToe-v0 | qwen/Qwen3-4B-Base | openai/gpt-4.1-mini | complete | loss | -1 | 1 | 6 | 29.638418 | [{"action":"[4]","env_id":"TicTacToe-v0","episode_id":471,"final_reward":0.0,"formatted_observation"(...TRUNCATED) | ["You are Player 0 in Tic Tac Toe.\nYour goal is to win three in a row (horizontally, vertically, or(...TRUNCATED) | ["","","","<|im_start|>user\nYou are playing a two-player zero-sum game. Make valid actions to win.\(...TRUNCATED) | ["","","","You are a helpful assistant.","","You are playing a two-player zero-sum game. Make valid (...TRUNCATED) | ["[4]","[bet]","[d]","","I have 10 Wood (value 5 each) and 10 Gold (value 15 each). To increase my t(...TRUNCATED) | [
0,
1,
0,
0,
0,
0,
0,
0,
1,
0,
1,
0,
1,
0,
0,
1,
1,
0,
1,
0,
0,
1,
1,
0,
1,
1,
0,
0,
1,
0,
1
] | ["openai/gpt-4.1-mini","openai/gpt-4.1-mini","openai/gpt-4.1-mini","qwen/Qwen3-4B-Base","openai/gpt-(...TRUNCATED) |
320 | TicTacToe-v0 | qwen/Qwen3-4B-Base | openai/gpt-4.1-mini | complete | loss | -1 | 1 | 8 | 22.575946 | [{"action":"[4]","env_id":"TicTacToe-v0","episode_id":320,"final_reward":0.0,"formatted_observation"(...TRUNCATED) | ["You are Player 0 in Tic Tac Toe.\nYour goal is to win three in a row (horizontally, vertically, or(...TRUNCATED) | ["","<|im_start|>user\nYou are playing a two-player zero-sum game. Make valid actions to win.\nObser(...TRUNCATED) | ["","Assistant: In this scenario, you are playing Kuhn Poker as Player 1 with the Queen (Q) card. Th(...TRUNCATED) | ["[4]","[check]","","9","[col 3]","[Bid: 2, 6]","[5]","","","[bet]","Hello! I have 10 Wood (value 15(...TRUNCATED) | [
0,
1,
0,
0,
0,
0,
0,
0,
1,
0,
1,
0,
1,
1,
1,
0,
1,
1,
0,
1,
1,
1,
0,
1,
1,
1,
1,
1,
0,
1,
0,
1,
1,
1,
0,
1
] | ["openai/gpt-4.1-mini","qwen/Qwen3-4B-Base","qwen/Qwen3-4B-Base","qwen/Qwen3-4B-Base","openai/gpt-4.(...TRUNCATED) |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- 4