Sync README with repo: drop device=cpu, drop ?nw, add return numbers

README.md

@@ -26,12 +26,14 @@ Stable under self-generated rollouts — long-horizon control without the drift
 
 ## Bundles in this repository
 
-| Environment | Subfolder |
-|---|---|
-| Ant-v5 | `ant-v5` |
-| HalfCheetah-v5 | `halfcheetah-v5` |
-| Walker2d-v5 | `walker2d-v5` |
-| Humanoid-v5 | `humanoid-v5` |
+| Environment | Subfolder | Return (mean ± std) |
+|---|---|---|
+| Ant-v5 | `ant-v5` | 3033 ± 895 |
+| HalfCheetah-v5 | `halfcheetah-v5` | 2066 ± 2776 |
+| Walker2d-v5 | `walker2d-v5` | 2961 ± 756 |
+| Humanoid-v5 | `humanoid-v5` | 3634 ± 2152 |
+
+Returns are over 5 episodes with `seed=0`, run on CPU via `run_episodes`.
 
 ## Quick Start
 
@@ -47,7 +49,6 @@ env = gym.make("Ant-v5")
 runner = load_runner_from_hub(
     repo_id="ccnets/causal-gpt-rl",
     subfolder="ant-v5",
-    device="cpu",
 )
 stats = run_episodes(env, runner, num_episodes=5, seed=0)
 print(stats["return_mean"], stats["return_std"])
@@ -64,7 +65,7 @@ Each subfolder contains:
 ## Links
 
 - **Code:** [github.com/ccnets-team/causal-gpt-rl](https://github.com/ccnets-team/causal-gpt-rl)
-- **Training logs (W&B):** [wandb.ai/junhopark/Causal GPT-RL](https://wandb.ai/junhopark/Causal%20GPT-RL?nw)
+- **Training logs (W&B):** [wandb.ai/junhopark/Causal GPT-RL](https://wandb.ai/junhopark/Causal%20GPT-RL)
 - **Website:** [ccnets.org](https://ccnets.org)
 
 ## License