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 19 | duration float64 1.04 208 | trajectory listlengths 44 103 | observations listlengths 44 103 | formatted_observations listlengths 44 103 | reasoning listlengths 44 103 | actions listlengths 44 103 | player_ids listlengths 44 103 | model_names listlengths 44 103 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
201 | TicTacToe-v0 | qwen/Qwen3-14B-Base | openai/gpt-4.1-mini | complete | loss | -1 | 1 | 11 | 56.742995 | [{"action":"[4]","env_id":"TicTacToe-v0","episode_id":201,"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) | ["","Given that you have the highest card (K) in the current round of Kuhn Poker, your optimal strat(...TRUNCATED) | ["[4]","[bet]","[Offer: 5 Wood -> 5 Gold] I'm willing to trade some of my wood for more gold. Let's (...TRUNCATED) | [0,1,0,0,0,0,0,0,1,0,1,0,1,1,1,1,1,0,0,1,0,0,1,0,1,1,1,1,1,0,1,1,0,0,0,1,1,0,1,1,0,0,0,1,0,0,0,1,0,0(...TRUNCATED) | ["openai/gpt-4.1-mini","qwen/Qwen3-14B-Base","qwen/Qwen3-14B-Base","qwen/Qwen3-14B-Base","qwen/Qwen3(...TRUNCATED) |
366 | TicTacToe-v0 | qwen/Qwen3-14B-Base | openai/gpt-4.1-mini | invalid | win | 0 | -1 | 3 | 16.314631 | [{"action":"[4]","env_id":"TicTacToe-v0","episode_id":366,"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.\(...TRUNCATED) | ["","","","### Understanding the Game Mechanics\n\nBefore diving into strategy, it's crucial to comp(...TRUNCATED) | ["[4]","[bet]","Hello! I have 10 Wood and 10 Gold, with values of 5 and 15 respectively. I’m inter(...TRUNCATED) | [0,1,0,0,0,0,0,0,1,0,1,1,1,1,1,1,0,0,0,0,0,0,0,1,1,1,1,0,0,1,0,0,0,0,1,1,0,0,1,1,1,0,0,1,0,0,0,1,1,0(...TRUNCATED) | ["openai/gpt-4.1-mini","openai/gpt-4.1-mini","openai/gpt-4.1-mini","qwen/Qwen3-14B-Base","qwen/Qwen3(...TRUNCATED) |
98 | TicTacToe-v0 | qwen/Qwen3-14B-Base | openai/gpt-4.1-mini | complete | loss | -1 | 1 | 6 | 35.19742 | [{"action":"[4]","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.\nOb(...TRUNCATED) | ["","","In Kuhn Poker, the game involves strategic decision-making based on the card you hold and th(...TRUNCATED) | ["[4]","I have 10 Wood (value 5 each) and 10 Gold (value 15 each). To increase my total value, I wan(...TRUNCATED) | [0,0,1,0,0,0,0,0,1,1,0,1,0,1,1,1,0,0,1,0,1,0,0,0,1,1,0,1,0,1,1,1,0,0,1,0,1,0,1,0,0,1,1,0,1,1,1,0,1,0(...TRUNCATED) | ["openai/gpt-4.1-mini","openai/gpt-4.1-mini","qwen/Qwen3-14B-Base","openai/gpt-4.1-mini","qwen/Qwen3(...TRUNCATED) |
129 | TicTacToe-v0 | qwen/Qwen3-14B-Base | openai/gpt-4.1-mini | invalid | win | 0 | -1 | 3 | 10.336217 | [{"action":"[4]","env_id":"TicTacToe-v0","episode_id":129,"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.\nOb(...TRUNCATED) | ["","","To analyze the current board state and determine the best move for snake 0, let's break down(...TRUNCATED) | ["[4]","[bet]","[w]","I'm open to negotiation. What resources do you have, and what would you like t(...TRUNCATED) | [0,1,0,0,0,0,0,0,1,0,1,1,1,1,1,1,0,0,0,0,0,0,1,1,1,0,1,1,1,1,1,0,0,0,0,0,1,1,1,1,0,0,0,0,1,1,1,1,0,0(...TRUNCATED) | ["openai/gpt-4.1-mini","openai/gpt-4.1-mini","qwen/Qwen3-14B-Base","qwen/Qwen3-14B-Base","openai/gpt(...TRUNCATED) |
450 | TicTacToe-v0 | qwen/Qwen3-14B-Base | openai/gpt-4.1-mini | invalid | loss | -1 | 0 | 11 | 94.014621 | [{"action":"[4]","env_id":"TicTacToe-v0","episode_id":450,"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.\nObser(...TRUNCATED) | ["","In Kuhn Poker, the strategy depends on the card you hold and the actions of your opponent. Sinc(...TRUNCATED) | ["[4]","[bet]","","[d]","[col 3]","[5]","[Bid: 2, 1]","[2 2]","0","[call]","Hello Player 0! I have a(...TRUNCATED) | [0,1,0,0,0,0,0,0,1,0,1,1,1,1,1,1,0,0,0,0,0,0,1,1,1,1,1,1,1,1,0,0,0,1,0,0,0,0,0,1,0,1,1,1,1,1,1,0,0,0(...TRUNCATED) | ["openai/gpt-4.1-mini","qwen/Qwen3-14B-Base","qwen/Qwen3-14B-Base","openai/gpt-4.1-mini","qwen/Qwen3(...TRUNCATED) |
70 | TicTacToe-v0 | qwen/Qwen3-14B-Base | openai/gpt-4.1-mini | complete | win | 1 | -1 | 4 | 15.603965 | [{"action":"[4]","env_id":"TicTacToe-v0","episode_id":70,"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) | ["The game is Tic Tac Toe, where Player 0 (you) is 'O' and Player 1 (the opponent) is 'X'. The curre(...TRUNCATED) | ["[4]","[check]","[d]","","[col 3]","","[5]","[2 5]","[0]","[check]","[d]","Hello Player 0! I have 1(...TRUNCATED) | [0,1,0,0,0,0,0,0,1,0,1,1,1,0,1,1,0,0,0,0,0,0,0,1,1,1,1,1,1,0,1,0,0,0,0,1,0,1,0,0,1,1,0,0,1,1,0,1,0,1(...TRUNCATED) | ["qwen/Qwen3-14B-Base","openai/gpt-4.1-mini","openai/gpt-4.1-mini","qwen/Qwen3-14B-Base","qwen/Qwen3(...TRUNCATED) |
127 | TicTacToe-v0 | qwen/Qwen3-14B-Base | openai/gpt-4.1-mini | complete | loss | -1 | 1 | 7 | 59.812124 | [{"action":"[4]","env_id":"TicTacToe-v0","episode_id":127,"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.\nObser(...TRUNCATED) | ["","[GAME] You are Player 1 in a 5-round game of Kuhn Poker. Your card is Q, and your available act(...TRUNCATED) | ["[4]","[bet]","[Offer: 5 Wood -> 3 Gold] I'm willing to trade some of my wood for gold. Let's see i(...TRUNCATED) | [0,1,0,0,0,0,0,0,1,0,1,1,1,0,1,1,0,0,0,0,1,1,1,1,1,1,1,0,1,0,0,0,0,0,1,1,1,1,1,0,0,0,0,0,1,1,1,1,1,0(...TRUNCATED) | ["openai/gpt-4.1-mini","qwen/Qwen3-14B-Base","qwen/Qwen3-14B-Base","openai/gpt-4.1-mini","openai/gpt(...TRUNCATED) |
433 | TicTacToe-v0 | qwen/Qwen3-14B-Base | openai/gpt-4.1-mini | complete | loss | -1 | 1 | 4 | 33.84658 | [{"action":"[4]","env_id":"TicTacToe-v0","episode_id":433,"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.\nObser(...TRUNCATED) | ["","In Kuhn Poker, the goal is to maximize your expected value by making decisions that are optimal(...TRUNCATED) | ["[4]","[bet]","I see you value Gold at 15 and Wood at 5. Since I currently have equal quantities of(...TRUNCATED) | [0,1,0,0,0,0,0,0,1,0,1,1,0,1,1,1,0,0,0,1,0,0,1,1,1,1,0,1,0,0,0,1,1,1,0,0,0,1,0,1,0,0,1,1,0,0,1,1,0,1(...TRUNCATED) | ["openai/gpt-4.1-mini","qwen/Qwen3-14B-Base","openai/gpt-4.1-mini","openai/gpt-4.1-mini","qwen/Qwen3(...TRUNCATED) |
295 | TicTacToe-v0 | qwen/Qwen3-14B-Base | openai/gpt-4.1-mini | complete | win | 1 | -1 | 7 | 40.356768 | [{"action":"[4]","env_id":"TicTacToe-v0","episode_id":295,"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.\nObser(...TRUNCATED) | ["","In Kuhn Poker, the strategy often involves bluffing and reading your opponent's moves. Since I (...TRUNCATED) | ["[4]","check","I have 10 Wood (value 5 each) and 10 Gold (value 15 each). I'm interested in increas(...TRUNCATED) | [0,1,0,0,0,0,0,0,1,0,1,1,1,1,1,1,0,1,0,0,0,0,0,0,1,0,1,1,1,1,1,1,0,1,0,0,0,0,1,0,1,1,1,1,1,0,1,0,0,0(...TRUNCATED) | ["openai/gpt-4.1-mini","qwen/Qwen3-14B-Base","openai/gpt-4.1-mini","openai/gpt-4.1-mini","qwen/Qwen3(...TRUNCATED) |
398 | TicTacToe-v0 | qwen/Qwen3-14B-Base | openai/gpt-4.1-mini | invalid | win | 0 | -1 | 3 | 23.257912 | [{"action":"[4]","env_id":"TicTacToe-v0","episode_id":398,"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) | ["I will aim for the center square (position 4) on my first move, as it provides the most flexibilit(...TRUNCATED) | ["[4]","[check]","[d]","I'm open to negotiation. [Offer: 3 Stone -> 2 Gold]","[col 3]","6","","[2 3](...TRUNCATED) | [0,1,0,0,0,0,0,0,1,0,1,0,1,1,0,1,0,1,0,1,0,0,1,1,0,1,0,1,1,0,1,0,1,0,0,1,1,0,1,1,0,1,0,0,1,0,1,0,1,1(...TRUNCATED) | ["qwen/Qwen3-14B-Base","qwen/Qwen3-14B-Base","openai/gpt-4.1-mini","qwen/Qwen3-14B-Base","openai/gpt(...TRUNCATED) |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- 5