anna4142 commited on
Commit
54736ca
1 Parent(s): d8b8e78

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. README.md +31 -0
  2. config.json +30 -0
  3. model.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ tags:
4
+ - decision-transformer
5
+ - reinforcement-learning
6
+ - hierarchical-learning
7
+ - hopper
8
+ license: mit
9
+ ---
10
+
11
+ # Hierarchical Decision Transformer for Hopper
12
+
13
+ This model extends the Decision Transformer architecture with hierarchical clustering capabilities for improved long-horizon task performance on the Hopper-v3 environment.
14
+
15
+ ## Model Description
16
+
17
+ - **Model Type:** Hierarchical Decision Transformer
18
+ - **Training Environment:** Hopper-v3
19
+ - **Input:** State observations (11 dimensions), desired returns
20
+ - **Output:** Actions (3 dimensions)
21
+ - **Architecture Features:**
22
+ - Hierarchical clustering head for subtask identification
23
+ - Subgoal-based weighting
24
+ - Multi-task capabilities
25
+
26
+ ## Usage
27
+
28
+ ```python
29
+ from transformers import DecisionTransformerModel
30
+ model = DecisionTransformerModel.from_pretrained("anna4142/hierarchical-decision-transformer")
31
+ ```
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "act_dim": 3,
3
+ "action_tanh": true,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "TrainableDT"
7
+ ],
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 50256,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
12
+ "hidden_size": 128,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "max_ep_len": 4096,
16
+ "model_type": "decision_transformer",
17
+ "n_head": 1,
18
+ "n_inner": null,
19
+ "n_layer": 3,
20
+ "n_positions": 1024,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "state_dim": 11,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.46.2",
28
+ "use_cache": true,
29
+ "vocab_size": 1
30
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c9445590e753ce9c656435bf1b414567f444e7ef00d4c6befe58c83812851f3
3
+ size 5025196