diff --git a/README.md b/README.md
index 8397c605..e58d107f 100644
--- a/README.md
+++ b/README.md
@@ -278,13 +278,15 @@ dynamic benchmarks.
 
 ## Variables
 Here's a list of relevant env. variables that are used by AgentLab:
-- `OPEAI_API_KEY` which is used by default for OpenAI LLMs.
+- `OPENAI_API_KEY` which is used by default for OpenAI LLMs.
 - `AZURE_OPENAI_API_KEY`, used by default for AzureOpenAI LLMs.
 - `AZURE_OPENAI_ENDPOINT` to specify your Azure endpoint.
 - `OPENAI_API_VERSION` for the Azure API.
 - `OPENROUTER_API_KEY` for the Openrouter API
 - `AGENTLAB_EXP_ROOT`, desired path for your experiments to be stored, defaults to `~/agentlab-results`.
 - `AGENTXRAY_SHARE_GRADIO`, which prompts AgentXRay to open a public tunnel on launch.
+- `RAY_PUBLIC_DASHBOARD` (true / false), used to specify whether the ray dashboard should be made publicly accessible (`0.0.0.0`) or not (`127.0.0.1`).
+- `RAY_DASHBOARD_PORT` (int), used to specify the port on which the ray dashboard should be accessible.
 
 ## Misc
 
diff --git a/src/agentlab/experiments/launch_exp.py b/src/agentlab/experiments/launch_exp.py
index f14ae4c7..199454c5 100644
--- a/src/agentlab/experiments/launch_exp.py
+++ b/src/agentlab/experiments/launch_exp.py
@@ -9,6 +9,7 @@
 from agentlab.experiments.loop import ExpArgs, yield_all_exp_results
 
 RAY_PUBLIC_DASHBOARD = os.environ.get("RAY_PUBLIC_DASHBOARD", "false") == "true"
+RAY_DASHBOARD_PORT = os.environ.get("RAY_DASHBOARD_PORT")
 
 
 def run_experiments(
@@ -86,7 +87,9 @@ def run_experiments(
             from agentlab.experiments.graph_execution_ray import execute_task_graph, ray
 
             ray.init(
-                num_cpus=n_jobs, dashboard_host="0.0.0.0" if RAY_PUBLIC_DASHBOARD else "127.0.0.1"
+                num_cpus=n_jobs,
+                dashboard_host="0.0.0.0" if RAY_PUBLIC_DASHBOARD else "127.0.0.1",
+                dashboard_port=None if RAY_DASHBOARD_PORT is None else int(RAY_DASHBOARD_PORT),
             )
             try:
                 execute_task_graph(exp_args_list, avg_step_timeout=avg_step_timeout)