lionel.xie

Results 4 issues of lionel.xie

InvalidArgumentError: Incompatible shapes: [8,514,768] vs. [8,512,768] [[{{node model_2/Embedding-Position/add}} = Add[T=DT_FLOAT, _class=["loc:@training/Adam/gradients/model_2/Embedding-Position/add_grad/Reshape"], _device="/job:localhost/replica:0/task:0/device:GPU:0"](model_2/Embedding-Token-Segment/add, model_2/Embedding-Position/Tile)]] [[{{node metrics/acc_top2/Mean_1/_3259}} = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_21926_metrics/acc_top2/Mean_1", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

I don't find code about "Inferring Policies of Ther Agents" and "Agent with Polivy Ensembles" mentioned in the paper 'Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments'.Did I miss something?

## What does this PR do? Add EnumNameSerializer for Enum, can config it by org.apache.fury.config.Config#useEnumNameSerializer, default value is false ## Related issues ## Does this PR introduce any user-facing change?...

## Is your feature request related to a problem? Please describe. Can fury support serializing enumerations by enumeration name? Serializing enumeration names like a string serializer. Serializing existing enumerations through...

enhancement