Commit
•
fcbbe46
1
Parent(s):
bce4ba7
Uploading flowers-team/TA_Random_SAC_bipedal_s1
Browse files- README.md +56 -0
- group1-shard1of1.bin +3 -0
- model.json +1 -0
- ta-config.json +1 -0
README.md
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- sac
|
4 |
+
- deep-reinforcement-learning
|
5 |
+
- reinforcement-learning
|
6 |
+
- teach-my-agent-parkour
|
7 |
+
model-index:
|
8 |
+
- name: Random_SAC_bipedal_s1
|
9 |
+
results:
|
10 |
+
- metrics:
|
11 |
+
- type: mean_reward
|
12 |
+
value: 169.61 +/- 124.96
|
13 |
+
name: mean_reward
|
14 |
+
task:
|
15 |
+
type: reinforcement-learning
|
16 |
+
name: reinforcement-learning
|
17 |
+
dataset:
|
18 |
+
name: teach-my-agent-parkour
|
19 |
+
type: teach-my-agent-parkour
|
20 |
+
---
|
21 |
+
|
22 |
+
# Deep RL Agent Playing TeachMyAgent's parkour.
|
23 |
+
You can find more info about TeachMyAgent [here](https://developmentalsystems.org/TeachMyAgent/).
|
24 |
+
|
25 |
+
Results of our benchmark can be found in our [paper](https://arxiv.org/pdf/2103.09815.pdf).
|
26 |
+
|
27 |
+
You can test this policy [here](https://huggingface.co/spaces/flowers-team/Interactive_DeepRL_Demo)
|
28 |
+
|
29 |
+
## Results
|
30 |
+
Percentage of mastered tasks (i.e. reward >= 230) after 20 millions steps on the Parkour track.
|
31 |
+
|
32 |
+
Results shown are averages over 16 seeds along with the standard deviation for each morphology as well as the aggregation of the 48 seeds in the *Overall* column.
|
33 |
+
|
34 |
+
We highlight the best results in bold.
|
35 |
+
|
36 |
+
| Algorithm | BipedalWalker | Fish | Climber | Overall |
|
37 |
+
|---------------|----------------|---------------|--------------|---------------|
|
38 |
+
| Random | 27.25 (± 10.7) | 23.6 (± 21.3) | 0.0 (± 0.0) | 16.9 (± 18.3) |
|
39 |
+
| ADR | 14.7 (± 19.4) | 5.3 (± 20.6) | 0.0 (± 0.0) | 6.7 (± 17.4) |
|
40 |
+
| ALP-GMM | **42.7** (± 11.2) | 36.1 (± 28.5) | 0.4 (± 1.2) | **26.4** (± 25.7) |
|
41 |
+
| Covar-GMM | 35.7 (± 15.9) | 29.9 (± 27.9) | 0.5 (± 1.9) | 22.1 (± 24.2) |
|
42 |
+
| GoalGAN | 25.4 (± 24.7) | 34.7 ± 37.0) | 0.8 (± 2.7) | 20.3 (± 29.5) |
|
43 |
+
| RIAC | 31.2 (± 8.2) | **37.4** (± 25.4) | 0.4 (± 1.4) | 23.0 (± 22.4) |
|
44 |
+
| SPDL | 30.6 (± 22.8) | 9.0 (± 24.2) | **1.0** (± 3.4) | 13.5 (± 23.0) |
|
45 |
+
| Setter-Solver | 28.75 (± 20.7) | 5.1 (± 7.6) | 0.0 (± 0.0) | 11.3 (± 17.9) |
|
46 |
+
|
47 |
+
# Hyperparameters
|
48 |
+
```python
|
49 |
+
{'student': 'SAC'
|
50 |
+
'environment': 'parkour'
|
51 |
+
'training_steps': 20000000
|
52 |
+
'n_evaluation_tasks': 100
|
53 |
+
'teacher': 'Random'
|
54 |
+
'morphology': 'old_classic_bipedal'}
|
55 |
+
```
|
56 |
+
|
group1-shard1of1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d71baa822a216e775414458d1e25a0905575dade751985971dc5eceab9542a82
|
3 |
+
size 2187660
|
model.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"format": "graph-model", "generatedBy": "1.15.3", "convertedBy": "TensorFlow.js Converter v3.19.0", "signature": {"inputs": {"x": {"name": "Placeholder_1:0", "dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "-1"}, {"size": "36"}]}}, "a": {"name": "Placeholder_2:0", "dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "-1"}, {"size": "4"}]}}}, "outputs": {"main/v/Squeeze:0": {"name": "main/v/Squeeze:0", "dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "-1"}]}}, "main/mul_1:0": {"name": "main/mul_1:0", "dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "-1"}, {"size": "4"}]}}, "main/q1/Squeeze:0": {"name": "main/q1/Squeeze:0", "dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "-1"}]}}, "main/mul:0": {"name": "main/mul:0", "dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "-1"}, {"size": "4"}]}}, "main/q2/Squeeze:0": {"name": "main/q2/Squeeze:0", "dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "-1"}]}}}}, "modelTopology": {"node": [{"name": "Placeholder_1", "op": "Placeholder", "attr": {"shape": {"shape": {"dim": [{"size": "-1"}, {"size": "36"}]}}, "dtype": {"type": "DT_FLOAT"}}}, {"name": "Placeholder_2", "op": "Placeholder", "attr": {"dtype": {"type": "DT_FLOAT"}, "shape": {"shape": {"dim": [{"size": "-1"}, {"size": "4"}]}}}}, {"name": "main/pi/dense/kernel", "op": "Const", "attr": {"value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "36"}, {"size": "400"}]}}}, "dtype": {"type": "DT_FLOAT"}}}, {"name": "main/v/dense_2/bias", "op": "Const", "attr": {"dtype": {"type": "DT_FLOAT"}, "value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "1"}]}}}}}, {"name": "main/pi/dense/bias", "op": "Const", "attr": {"dtype": {"type": "DT_FLOAT"}, "value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "400"}]}}}}}, {"name": "main/q2/dense/kernel", "op": "Const", "attr": {"value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "40"}, {"size": "400"}]}}}, "dtype": {"type": "DT_FLOAT"}}}, {"name": "main/q2/dense_2/bias", "op": "Const", "attr": {"value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "1"}]}}}, "dtype": {"type": "DT_FLOAT"}}}, {"name": "main/pi/dense_1/kernel", "op": "Const", "attr": {"value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "400"}, {"size": "300"}]}}}, "dtype": {"type": "DT_FLOAT"}}}, {"name": "main/q2/dense_1/bias", "op": "Const", "attr": {"value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "300"}]}}}, "dtype": {"type": "DT_FLOAT"}}}, {"name": "main/v/dense_2/kernel", "op": "Const", "attr": {"dtype": {"type": "DT_FLOAT"}, "value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "300"}, {"size": "1"}]}}}}}, {"name": "main/pi/dense_1/bias", "op": "Const", "attr": {"value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "300"}]}}}, "dtype": {"type": "DT_FLOAT"}}}, {"name": "main/q2/dense/bias", "op": "Const", "attr": {"dtype": {"type": "DT_FLOAT"}, "value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "400"}]}}}}}, {"name": "main/pi/dense_2/kernel", "op": "Const", "attr": {"dtype": {"type": "DT_FLOAT"}, "value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "300"}, {"size": "4"}]}}}}}, {"name": "main/pi/dense_2/bias", "op": "Const", "attr": {"dtype": {"type": "DT_FLOAT"}, "value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "4"}]}}}}}, {"name": "main/v/dense/kernel", "op": "Const", "attr": {"dtype": {"type": "DT_FLOAT"}, "value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "36"}, {"size": "400"}]}}}}}, {"name": "main/pi/dense_3/kernel", "op": "Const", "attr": {"dtype": {"type": "DT_FLOAT"}, "value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "300"}, {"size": "4"}]}}}}}, {"name": "main/v/dense_1/bias", "op": "Const", "attr": {"dtype": {"type": "DT_FLOAT"}, "value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "300"}]}}}}}, {"name": "main/pi/dense_3/bias", "op": "Const", "attr": {"dtype": {"type": "DT_FLOAT"}, "value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "4"}]}}}}}, {"name": "main/pi/add/y", "op": "Const", "attr": {"dtype": {"type": "DT_FLOAT"}, "value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {}}}}}, {"name": "main/pi/mul/x", "op": "Const", "attr": {"value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {}}}, "dtype": {"type": "DT_FLOAT"}}}, {"name": "main/pi/add_1/x", "op": "Const", "attr": {"value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {}}}, "dtype": {"type": "DT_FLOAT"}}}, {"name": "main/q1/concat/axis", "op": "Const", "attr": {"dtype": {"type": "DT_INT32"}, "value": {"tensor": {"dtype": "DT_INT32", "tensorShape": {}}}}}, {"name": "main/q1/dense/kernel", "op": "Const", "attr": {"dtype": {"type": "DT_FLOAT"}, "value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "40"}, {"size": "400"}]}}}}}, {"name": "main/v/dense/bias", "op": "Const", "attr": {"dtype": {"type": "DT_FLOAT"}, "value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "400"}]}}}}}, {"name": "main/q1/dense/bias", "op": "Const", "attr": {"dtype": {"type": "DT_FLOAT"}, "value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "400"}]}}}}}, {"name": "main/q2/dense_2/kernel", "op": "Const", "attr": {"dtype": {"type": "DT_FLOAT"}, "value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "300"}, {"size": "1"}]}}}}}, {"name": "main/q1/dense_1/kernel", "op": "Const", "attr": {"value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "400"}, {"size": "300"}]}}}, "dtype": {"type": "DT_FLOAT"}}}, {"name": "main/q1/dense_1/bias", "op": "Const", "attr": {"dtype": {"type": "DT_FLOAT"}, "value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "300"}]}}}}}, {"name": "main/q1/dense_2/kernel", "op": "Const", "attr": {"value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "300"}, {"size": "1"}]}}}, "dtype": {"type": "DT_FLOAT"}}}, {"name": "main/q2/dense_1/kernel", "op": "Const", "attr": {"value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "400"}, {"size": "300"}]}}}, "dtype": {"type": "DT_FLOAT"}}}, {"name": "main/v/dense_1/kernel", "op": "Const", "attr": {"dtype": {"type": "DT_FLOAT"}, "value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "400"}, {"size": "300"}]}}}}}, {"name": "main/q1/dense_2/bias", "op": "Const", "attr": {"dtype": {"type": "DT_FLOAT"}, "value": {"tensor": {"dtype": "DT_FLOAT", "tensorShape": {"dim": [{"size": "1"}]}}}}}, {"name": "main/pi/dense/Relu", "op": "_FusedMatMul", "input": ["Placeholder_1", "main/pi/dense/kernel", "main/pi/dense/bias"], "device": "/device:CPU:0", "attr": {"transpose_b": {"b": false}, "T": {"type": "DT_FLOAT"}, "num_args": {"i": "1"}, "epsilon": {"f": 0.0}, "transpose_a": {"b": false}, "fused_ops": {"list": {"s": ["Qmlhc0FkZA==", "UmVsdQ=="]}}}}, {"name": "main/q1/concat", "op": "ConcatV2", "input": ["Placeholder_1", "Placeholder_2", "main/q1/concat/axis"], "attr": {"Tidx": {"type": "DT_INT32"}, "N": {"i": "2"}, "T": {"type": "DT_FLOAT"}}}, {"name": "main/v/dense/Relu", "op": "_FusedMatMul", "input": ["Placeholder_1", "main/v/dense/kernel", "main/v/dense/bias"], "device": "/device:CPU:0", "attr": {"epsilon": {"f": 0.0}, "num_args": {"i": "1"}, "transpose_b": {"b": false}, "transpose_a": {"b": false}, "fused_ops": {"list": {"s": ["Qmlhc0FkZA==", "UmVsdQ=="]}}, "T": {"type": "DT_FLOAT"}}}, {"name": "main/pi/dense_1/Relu", "op": "_FusedMatMul", "input": ["main/pi/dense/Relu", "main/pi/dense_1/kernel", "main/pi/dense_1/bias"], "device": "/device:CPU:0", "attr": {"fused_ops": {"list": {"s": ["Qmlhc0FkZA==", "UmVsdQ=="]}}, "T": {"type": "DT_FLOAT"}, "num_args": {"i": "1"}, "epsilon": {"f": 0.0}, "transpose_b": {"b": false}, "transpose_a": {"b": false}}}, {"name": "main/q2/dense/Relu", "op": "_FusedMatMul", "input": ["main/q1/concat", "main/q2/dense/kernel", "main/q2/dense/bias"], "device": "/device:CPU:0", "attr": {"transpose_a": {"b": false}, "transpose_b": {"b": false}, "fused_ops": {"list": {"s": ["Qmlhc0FkZA==", "UmVsdQ=="]}}, "T": {"type": "DT_FLOAT"}, "epsilon": {"f": 0.0}, "num_args": {"i": "1"}}}, {"name": "main/q1/dense/Relu", "op": "_FusedMatMul", "input": ["main/q1/concat", "main/q1/dense/kernel", "main/q1/dense/bias"], "device": "/device:CPU:0", "attr": {"num_args": {"i": "1"}, "transpose_a": {"b": false}, "transpose_b": {"b": false}, "epsilon": {"f": 0.0}, "T": {"type": "DT_FLOAT"}, "fused_ops": {"list": {"s": ["Qmlhc0FkZA==", "UmVsdQ=="]}}}}, {"name": "main/v/dense_1/Relu", "op": "_FusedMatMul", "input": ["main/v/dense/Relu", "main/v/dense_1/kernel", "main/v/dense_1/bias"], "device": "/device:CPU:0", "attr": {"epsilon": {"f": 0.0}, "num_args": {"i": "1"}, "fused_ops": {"list": {"s": ["Qmlhc0FkZA==", "UmVsdQ=="]}}, "T": {"type": "DT_FLOAT"}, "transpose_b": {"b": false}, "transpose_a": {"b": false}}}, {"name": "main/pi/dense_2/BiasAdd", "op": "_FusedMatMul", "input": ["main/pi/dense_1/Relu", "main/pi/dense_2/kernel", "main/pi/dense_2/bias"], "device": "/device:CPU:0", "attr": {"T": {"type": "DT_FLOAT"}, "epsilon": {"f": 0.0}, "num_args": {"i": "1"}, "transpose_b": {"b": false}, "fused_ops": {"list": {"s": ["Qmlhc0FkZA=="]}}, "transpose_a": {"b": false}}}, {"name": "main/pi/dense_3/BiasAdd", "op": "_FusedMatMul", "input": ["main/pi/dense_1/Relu", "main/pi/dense_3/kernel", "main/pi/dense_3/bias"], "device": "/device:CPU:0", "attr": {"transpose_a": {"b": false}, "num_args": {"i": "1"}, "transpose_b": {"b": false}, "epsilon": {"f": 0.0}, "T": {"type": "DT_FLOAT"}, "fused_ops": {"list": {"s": ["Qmlhc0FkZA=="]}}}}, {"name": "main/q2/dense_1/Relu", "op": "_FusedMatMul", "input": ["main/q2/dense/Relu", "main/q2/dense_1/kernel", "main/q2/dense_1/bias"], "device": "/device:CPU:0", "attr": {"epsilon": {"f": 0.0}, "transpose_b": {"b": false}, "T": {"type": "DT_FLOAT"}, "transpose_a": {"b": false}, "fused_ops": {"list": {"s": ["Qmlhc0FkZA==", "UmVsdQ=="]}}, "num_args": {"i": "1"}}}, {"name": "main/q1/dense_1/Relu", "op": "_FusedMatMul", "input": ["main/q1/dense/Relu", "main/q1/dense_1/kernel", "main/q1/dense_1/bias"], "device": "/device:CPU:0", "attr": {"transpose_a": {"b": false}, "fused_ops": {"list": {"s": ["Qmlhc0FkZA==", "UmVsdQ=="]}}, "transpose_b": {"b": false}, "num_args": {"i": "1"}, "epsilon": {"f": 0.0}, "T": {"type": "DT_FLOAT"}}}, {"name": "main/v/dense_2/BiasAdd", "op": "_FusedMatMul", "input": ["main/v/dense_1/Relu", "main/v/dense_2/kernel", "main/v/dense_2/bias"], "device": "/device:CPU:0", "attr": {"transpose_b": {"b": false}, "epsilon": {"f": 0.0}, "fused_ops": {"list": {"s": ["Qmlhc0FkZA=="]}}, "T": {"type": "DT_FLOAT"}, "num_args": {"i": "1"}, "transpose_a": {"b": false}}}, {"name": "main/pi/Shape", "op": "Shape", "input": ["main/pi/dense_2/BiasAdd"], "attr": {"T": {"type": "DT_FLOAT"}, "out_type": {"type": "DT_INT32"}}}, {"name": "main/pi/Tanh", "op": "Tanh", "input": ["main/pi/dense_2/BiasAdd"], "attr": {"T": {"type": "DT_FLOAT"}}}, {"name": "main/pi/dense_3/Tanh", "op": "Tanh", "input": ["main/pi/dense_3/BiasAdd"], "attr": {"T": {"type": "DT_FLOAT"}}}, {"name": "main/q2/dense_2/BiasAdd", "op": "_FusedMatMul", "input": ["main/q2/dense_1/Relu", "main/q2/dense_2/kernel", "main/q2/dense_2/bias"], "device": "/device:CPU:0", "attr": {"fused_ops": {"list": {"s": ["Qmlhc0FkZA=="]}}, "T": {"type": "DT_FLOAT"}, "transpose_a": {"b": false}, "num_args": {"i": "1"}, "epsilon": {"f": 0.0}, "transpose_b": {"b": false}}}, {"name": "main/q1/dense_2/BiasAdd", "op": "_FusedMatMul", "input": ["main/q1/dense_1/Relu", "main/q1/dense_2/kernel", "main/q1/dense_2/bias"], "device": "/device:CPU:0", "attr": {"transpose_b": {"b": false}, "fused_ops": {"list": {"s": ["Qmlhc0FkZA=="]}}, "num_args": {"i": "1"}, "T": {"type": "DT_FLOAT"}, "epsilon": {"f": 0.0}, "transpose_a": {"b": false}}}, {"name": "main/v/Squeeze", "op": "Squeeze", "input": ["main/v/dense_2/BiasAdd"], "attr": {"T": {"type": "DT_FLOAT"}, "squeeze_dims": {"list": {"i": ["1"]}}}}, {"name": "main/pi/random_normal/RandomStandardNormal", "op": "RandomStandardNormal", "input": ["main/pi/Shape"], "attr": {"T": {"type": "DT_INT32"}, "seed": {"i": "0"}, "dtype": {"type": "DT_FLOAT"}, "seed2": {"i": "0"}}}, {"name": "main/mul", "op": "Identity", "input": ["main/pi/Tanh"], "attr": {"T": {"type": "DT_FLOAT"}}}, {"name": "main/pi/add", "op": "AddV2", "input": ["main/pi/add/y", "main/pi/dense_3/Tanh"], "attr": {"T": {"type": "DT_FLOAT"}}}, {"name": "main/q2/Squeeze", "op": "Squeeze", "input": ["main/q2/dense_2/BiasAdd"], "attr": {"squeeze_dims": {"list": {"i": ["1"]}}, "T": {"type": "DT_FLOAT"}}}, {"name": "main/q1/Squeeze", "op": "Squeeze", "input": ["main/q1/dense_2/BiasAdd"], "attr": {"T": {"type": "DT_FLOAT"}, "squeeze_dims": {"list": {"i": ["1"]}}}}, {"name": "main/pi/mul", "op": "Mul", "input": ["main/pi/add", "main/pi/mul/x"], "attr": {"T": {"type": "DT_FLOAT"}}}, {"name": "main/pi/add_1", "op": "AddV2", "input": ["main/pi/add_1/x", "main/pi/mul"], "attr": {"T": {"type": "DT_FLOAT"}}}, {"name": "main/pi/Exp", "op": "Exp", "input": ["main/pi/add_1"], "attr": {"T": {"type": "DT_FLOAT"}}}, {"name": "main/pi/mul_1", "op": "Mul", "input": ["main/pi/Exp", "main/pi/random_normal/RandomStandardNormal"], "attr": {"T": {"type": "DT_FLOAT"}}}, {"name": "main/pi/add_2", "op": "AddV2", "input": ["main/pi/dense_2/BiasAdd", "main/pi/mul_1"], "attr": {"T": {"type": "DT_FLOAT"}}}, {"name": "main/pi/Tanh_1", "op": "Tanh", "input": ["main/pi/add_2"], "attr": {"T": {"type": "DT_FLOAT"}}}, {"name": "main/mul_1", "op": "Identity", "input": ["main/pi/Tanh_1"], "attr": {"T": {"type": "DT_FLOAT"}}}], "library": {}, "versions": {}}, "weightsManifest": [{"paths": ["group1-shard1of1.bin"], "weights": [{"name": "main/pi/dense/kernel", "shape": [36, 400], "dtype": "float32"}, {"name": "main/v/dense_2/bias", "shape": [1], "dtype": "float32"}, {"name": "main/pi/dense/bias", "shape": [400], "dtype": "float32"}, {"name": "main/q2/dense/kernel", "shape": [40, 400], "dtype": "float32"}, {"name": "main/q2/dense_2/bias", "shape": [1], "dtype": "float32"}, {"name": "main/pi/dense_1/kernel", "shape": [400, 300], "dtype": "float32"}, {"name": "main/q2/dense_1/bias", "shape": [300], "dtype": "float32"}, {"name": "main/v/dense_2/kernel", "shape": [300, 1], "dtype": "float32"}, {"name": "main/pi/dense_1/bias", "shape": [300], "dtype": "float32"}, {"name": "main/q2/dense/bias", "shape": [400], "dtype": "float32"}, {"name": "main/pi/dense_2/kernel", "shape": [300, 4], "dtype": "float32"}, {"name": "main/pi/dense_2/bias", "shape": [4], "dtype": "float32"}, {"name": "main/v/dense/kernel", "shape": [36, 400], "dtype": "float32"}, {"name": "main/pi/dense_3/kernel", "shape": [300, 4], "dtype": "float32"}, {"name": "main/v/dense_1/bias", "shape": [300], "dtype": "float32"}, {"name": "main/pi/dense_3/bias", "shape": [4], "dtype": "float32"}, {"name": "main/pi/add/y", "shape": [], "dtype": "float32"}, {"name": "main/pi/mul/x", "shape": [], "dtype": "float32"}, {"name": "main/pi/add_1/x", "shape": [], "dtype": "float32"}, {"name": "main/q1/concat/axis", "shape": [], "dtype": "int32"}, {"name": "main/q1/dense/kernel", "shape": [40, 400], "dtype": "float32"}, {"name": "main/v/dense/bias", "shape": [400], "dtype": "float32"}, {"name": "main/q1/dense/bias", "shape": [400], "dtype": "float32"}, {"name": "main/q2/dense_2/kernel", "shape": [300, 1], "dtype": "float32"}, {"name": "main/q1/dense_1/kernel", "shape": [400, 300], "dtype": "float32"}, {"name": "main/q1/dense_1/bias", "shape": [300], "dtype": "float32"}, {"name": "main/q1/dense_2/kernel", "shape": [300, 1], "dtype": "float32"}, {"name": "main/q2/dense_1/kernel", "shape": [400, 300], "dtype": "float32"}, {"name": "main/v/dense_1/kernel", "shape": [400, 300], "dtype": "float32"}, {"name": "main/q1/dense_2/bias", "shape": [1], "dtype": "float32"}]}]}
|
ta-config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"seed": 1, "morphology": "bipedal", "name": "Random_SAC_bipedal_s1"}
|